© 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. 2-RES-JB
    11. 8396
    Prev
    Next
    INDEX
    Explanations

    antiheroic or villainous characters with the surname "Hutchinson"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Hutch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.81
     corrid
    -0.76
    cycl
    -0.73
    cas
    -0.71
     appet
    -0.70
    hig
    -0.68
     acid
    -0.68
     acids
    -0.67
     sheets
    -0.67
     contrace
    -0.66
    POSITIVE LOGITS
    sburgh
    0.86
    utch
    0.82
    ainment
    0.82
    ansen
    0.78
    abe
    0.76
    icago
    0.75
    inson
    0.75
    OPLE
    0.74
    EEP
    0.73
    sonian
    0.70
    Activations Density 0.022%

    No Known Activations