© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35475
    Prev
    Next
    INDEX
    Explanations

    phrases related to microservices or small scale technological components

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.7%
    575
    +0.14
    0.7%
    60
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.05
    102
    +0.14
    0.11
    442
    +0.12
    0.06
    Negative Logits
    swick
    -0.78
    UAL
    -0.74
     Guilty
    -0.74
     Rack
    -0.69
    igham
    -0.67
    aukee
    -0.65
     Hurricanes
    -0.65
     eminent
    -0.65
     Bleach
    -0.63
    éĹĺ
    -0.63
    POSITIVE LOGITS
    organisms
    1.18
    seconds
    1.17
    gravity
    1.09
    cos
    1.05
    bial
    1.00
    enter
    0.93
    chip
    0.92
    economic
    0.90
    cephal
    0.89
    processor
    0.88
    Activations Density 6.236%

    No Known Activations