© 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. 24180
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase ", if" is used

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or hypothetical questions

    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
    mor
    -0.73
    selves
    -0.69
    ername
    -0.68
    gow
    -0.67
    gall
    -0.67
     gobl
    -0.66
    ords
    -0.66
    staking
    -0.61
     corrid
    -0.61
    MSN
    -0.60
    POSITIVE LOGITS
     except
    0.72
     uh
    0.69
     alas
    0.68
     although
    0.66
     please
    0.66
     however
    0.63
     besides
    0.62
     let
    0.61
     according
    0.61
    ean
    0.61
    Activations Density 0.220%

    No Known Activations