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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35059
    Prev
    Next
    INDEX
    Explanations

    phrases related to ruling out possibilities

    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
    447
    +0.20
    1.2%
    541
    +0.10
    0.6%
    169
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.20
    -0.10
    535
    +0.10
    0.03
    77
    +0.09
    0.04
    Negative Logits
    awar
    -0.69
    omsky
    -0.61
    ombat
    -0.60
    antry
    -0.59
    cue
    -0.59
    eworld
    -0.57
    artist
    -0.56
    BAT
    -0.55
    oppy
    -0.55
    eatured
    -0.55
    POSITIVE LOGITS
    posts
    0.65
     anything
    0.59
    nels
    0.57
     EVs
    0.55
     foul
    0.53
     hypot
    0.53
     possibility
    0.53
     positives
    0.52
     outright
    0.52
    enance
    0.52
    Activations Density 5.254%

    No Known Activations