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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34137
    Prev
    Next
    INDEX
    Explanations

    message logs from a chat platform

    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
    430
    +0.13
    0.5%
    384
    +0.12
    0.5%
    378
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.05
    176
    +0.12
    0.04
    380
    +0.11
    0.03
    Negative Logits
     helicop
    -1.02
    pread
    -0.93
     redes
    -0.87
    Bey
    -0.81
     psychiat
    -0.81
    theless
    -0.81
    odon
    -0.81
     Palest
    -0.80
     unpop
    -0.79
     enthusi
    -0.79
    POSITIVE LOGITS
     Entered
    1.06
    İ
    0.94
     Noticed
    0.92
     partName
    0.91
     Identified
    0.89
     =================================
    0.88
     Achievements
    0.88
     INFO
    0.88
     ]
    0.87
     Advice
    0.86
    Activations Density 1.655%

    No Known Activations