© 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. 18053
    Prev
    Next
    INDEX
    Explanations

    names of notable figures or entities in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and organizations

    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
    volent
    -0.74
    liest
    -0.68
    cially
    -0.66
    arently
    -0.66
    bidden
    -0.65
    imately
    -0.64
    successfully
    -0.63
    staking
    -0.62
    exempt
    -0.61
    etheus
    -0.61
    POSITIVE LOGITS
    ussian
    0.69
    sylv
    0.68
    onian
    0.68
    Dun
    0.68
    Ms
    0.67
    Mech
    0.66
     Scores
    0.66
    Mo
    0.65
    inian
    0.65
    ussie
    0.64
    Activations Density 0.352%

    No Known Activations