© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13748
    Prev
    Next
    INDEX
    Explanations

    memories or references to memory

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.13
    0.5%
    571
    +0.12
    0.5%
    249
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.07
    641
    +0.12
    0.06
    575
    +0.11
    0.06
    Negative Logits
    annis
    -0.77
     Galile
    -0.73
    retty
    -0.73
    etheus
    -0.72
    hat
    -0.72
    adiator
    -0.71
    govtrack
    -0.70
    paio
    -0.70
    assis
    -0.70
    Div
    -0.69
    POSITIVE LOGITS
     Memories
    1.09
    remember
    0.98
     recollection
    0.97
     memories
    0.91
     remembered
    0.88
    abilia
    0.86
     remembrance
    0.86
     remembering
    0.83
     vividly
    0.81
     remem
    0.81
    Activations Density 0.638%

    No Known Activations