© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12669
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities, particularly related to investigations

    oai_token-act-pair · gpt-3.5-turbo

    the name "Starr" along with other related entities or terms in a legal or investigative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berman
    -0.95
    glers
    -0.89
    ĨĴ
    -0.84
    lete
    -0.79
    hl
    -0.74
     conting
    -0.71
    achev
    -0.70
    gypt
    -0.70
    awei
    -0.70
    lect
    -0.70
    POSITIVE LOGITS
    ioned
    0.82
    igmatic
    0.74
    ional
    0.73
    wcsstore
    0.71
    ion
    0.69
    ners
    0.65
    esque
    0.64
    forth
    0.63
    ively
    0.61
    ious
    0.61
    Activations Density 0.107%

    No Known Activations