© 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. 39881
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical values related to various subjects such as sports, electricity consumption, and trades

    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
    +0.35
    1.7%
    497
    +0.13
    0.6%
    685
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.35
    0.33
    314
    +0.13
    -0.10
    127
    +0.12
    0.09
    Negative Logits
     Ares
    -0.65
     SCP
    -0.65
     SET
    -0.63
    EStreamFrame
    -0.62
     Accountability
    -0.62
     Jiu
    -0.61
     Suite
    -0.58
     âĵĺ
    -0.57
     ISS
    -0.57
     TOP
    -0.56
    POSITIVE LOGITS
    26
    1.17
    28
    1.16
    23
    1.15
    24
    1.15
    29
    1.15
    25
    1.14
    35
    1.14
    45
    1.13
    27
    1.11
    36
    1.11
    Activations Density 21.425%

    No Known Activations