© 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 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. 33414
    Prev
    Next
    INDEX
    Explanations

    text related to various data and information without a clear thematic pattern

    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
    526
    +0.16
    0.6%
    216
    +0.14
    0.6%
    726
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.16
    0.44
    138
    +0.14
    0.42
    64
    +0.14
    -0.18
    Negative Logits
    yip
    -1.00
    pton
    -0.98
    pheus
    -0.93
    pared
    -0.91
    senal
    -0.90
    perty
    -0.89
    chy
    -0.89
    cci
    -0.88
    hood
    -0.84
    hov
    -0.84
    POSITIVE LOGITS
    rophe
    1.31
    efully
    1.14
    rophic
    1.12
    roph
    1.12
    eful
    1.11
    rup
    1.06
    ruct
    1.05
    hest
    1.02
    odon
    1.01
    rop
    1.00
    Activations Density 9.355%

    No Known Activations