© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40946
    Prev
    Next
    INDEX
    Explanations

    words related to avant-garde art, cultural sensibilities, and experimental spaces

    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
    187
    +0.08
    0.8%
    647
    +0.06
    0.5%
    746
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.27
    326
    +0.06
    0.28
    187
    +0.05
    0.12
    Negative Logits
     backlog
    -0.37
    mington
    -0.35
     bund
    -0.34
    ODUCT
    -0.34
     Kodi
    -0.34
     discount
    -0.34
    è¦ļéĨĴ
    -0.33
     marrow
    -0.31
     confidentiality
    -0.30
     Revenue
    -0.30
    POSITIVE LOGITS
    ility
    0.45
    gard
    0.43
    ormal
    0.42
    edu
    0.42
    ean
    0.39
    ofi
    0.39
    lasses
    0.38
    atted
    0.38
    ilet
    0.38
    aza
    0.38
    Activations Density 11.705%

    No Known Activations