Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34560
    Prev
    Next
    INDEX
    Explanations

    timestamps and commands related to reading patch data in a Minecraft server log

    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
    211
    +0.13
    0.5%
    585
    +0.12
    0.5%
    640
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.18
    176
    +0.12
    0.06
    289
    +0.12
    -0.02
    Negative Logits
    oire
    -0.94
    reviewed
    -0.87
    izont
    -0.87
    âĸł
    -0.86
    roy
    -0.85
    iolet
    -0.85
    ité
    -0.84
     arrang
    -0.84
      
    -0.84
    âĺħ
    -0.83
    POSITIVE LOGITS
    Cache
    1.07
     Calls
    1.00
     000000
    0.97
     Cache
    0.97
     Client
    0.95
     ERROR
    0.91
     cache
    0.90
     hash
    0.90
     debug
    0.89
    filename
    0.89
    Activations Density 6.296%

    No Known Activations