© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 13228
    Prev
    Next
    INDEX
    Explanations

    medical conditions, specifically pertaining to the brain and energy

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with specific subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĮ
    -0.74
    omever
    -0.74
    abwe
    -0.72
    selves
    -0.71
    itored
    -0.69
    DonaldTrump
    -0.69
    ceive
    -0.69
    âĢ¢âĢ¢
    -0.68
    tnc
    -0.68
    thood
    -0.67
    POSITIVE LOGITS
     question
    0.72
     dilemma
    0.68
     shortage
    0.65
    oret
    0.63
     analogy
    0.61
     committee
    0.60
     grate
    0.60
     meanwhile
    0.60
    ultimate
    0.59
    iest
    0.58
    Activations Density 0.642%

    No Known Activations