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. 45739
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs related to actions, beliefs, or emotions

    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
    481
    +0.18
    0.8%
    447
    +0.15
    0.7%
    579
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.18
    0.19
    14
    +0.15
    0.04
    457
    +0.13
    0.07
    Negative Logits
    enhagen
    -0.85
    itars
    -0.74
    ullivan
    -0.68
    pages
    -0.67
    aus
    -0.67
    oshenko
    -0.66
    igham
    -0.65
    ansk
    -0.64
    OHN
    -0.64
     suspic
    -0.64
    POSITIVE LOGITS
     ourselves
    0.84
     myself
    0.82
     progresses
    0.78
     comprom
    0.73
     educator
    0.72
     extraord
    0.69
     proud
    0.69
     empath
    0.68
    olphin
    0.68
     witness
    0.67
    Activations Density 12.080%

    No Known Activations