© 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. 9-RES-JB
    11. 1595
    Prev
    Next
    INDEX
    Explanations

    references to family members and their relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.74
     themselves
    -0.69
     Pwr
    -0.67
    arnaev
    -0.66
    ensus
    -0.65
    ailability
    -0.63
    ettlement
    -0.63
    indal
    -0.62
    afort
    -0.62
    ablishment
    -0.61
    POSITIVE LOGITS
     loves
    0.84
    ÃŃs
    0.83
    my
    0.81
     smokes
    0.78
    friend
    0.75
     hates
    0.73
     hooked
    0.72
     todd
    0.71
     loved
    0.70
    Dad
    0.69
    Activations Density 0.146%

    No Known Activations