© 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. 8-RES-JB
    11. 17059
    Prev
    Next
    INDEX
    Explanations

    instances where a phrase or sentence ends with a comma

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a cause or consequence in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iph
    -0.85
    ulp
    -0.82
    opsis
    -0.76
    ete
    -0.73
    ona
    -0.73
    au
    -0.72
    ibo
    -0.71
    ":"/
    -0.66
    du
    -0.65
    Eye
    -0.65
    POSITIVE LOGITS
     respectively
    1.15
     culminating
    0.76
     embattled
    0.71
     proponents
    0.69
     lawmakers
    0.68
     adherents
    0.66
     analysts
    0.65
     researchers
    0.64
     critics
    0.63
     legislators
    0.63
    Activations Density 0.286%

    No Known Activations