© 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. 39493
    Prev
    Next
    INDEX
    Explanations

    timestamps and chat conversation patterns within a digital communication platform

    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
    342
    +0.13
    0.5%
    326
    +0.13
    0.5%
    568
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.13
    0.04
    568
    +0.13
    0.03
    201
    +0.13
    0.04
    Negative Logits
    avorite
    -0.98
     pse
    -0.97
    ulet
    -0.96
    ModLoader
    -0.89
    aditional
    -0.88
     carbohyd
    -0.87
    irlf
    -0.83
     nep
    -0.83
    ãĥĭ
    -0.82
     belonged
    -0.81
    POSITIVE LOGITS
     <+
    1.09
     <@
    0.93
     PM
    0.92
     CentOS
    0.90
     partName
    0.86
    PM
    0.86
     EVE
    0.85
    uty
    0.85
     Edited
    0.85
     raspberry
    0.84
    Activations Density 4.052%

    No Known Activations