© 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. 34852
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequence of events

    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
    +0.08
    0.8%
    699
    +0.06
    0.5%
    701
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.08
    0.12
    114
    +0.06
    0.10
    678
    +0.05
    0.10
    Negative Logits
     stakes
    -0.29
    ility
    -0.29
     welf
    -0.28
    Winged
    -0.28
     contradiction
    -0.28
     encouragement
    -0.28
    fighter
    -0.27
    ciplinary
    -0.27
     Peninsula
    -0.27
    borgh
    -0.27
    POSITIVE LOGITS
    Ń·
    0.44
    abouts
    0.41
    ettings
    0.39
    EStream
    0.39
    atra
    0.37
    utm
    0.36
    orm
    0.36
    orthy
    0.36
    nih
    0.36
    daq
    0.34
    Activations Density 11.465%

    No Known Activations