© 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. 10244
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive qualities and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions indicating connections or relationships between ideas

    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
    ESE
    -0.80
    odcast
    -0.76
    nik
    -0.73
    hov
    -0.72
    cko
    -0.72
    ilk
    -0.71
    kees
    -0.71
    ETS
    -0.70
    wire
    -0.70
    ATS
    -0.69
    POSITIVE LOGITS
     thus
    0.91
     therefore
    0.91
     consequently
    0.86
     creativity
    0.85
     feelings
    0.84
     awe
    0.84
     hence
    0.84
     excitement
    0.83
     thereby
    0.82
     accomplishments
    0.79
    Activations Density 0.588%

    No Known Activations