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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22539
    Prev
    Next
    INDEX
    Explanations

    names of individuals in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    names of people and characters

    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
    nai
    -0.83
    ĩ
    -0.82
    uments
    -0.74
    kaya
    -0.73
    ENCY
    -0.73
    ents
    -0.72
    acters
    -0.69
    nance
    -0.67
    ences
    -0.67
    omen
    -0.67
    POSITIVE LOGITS
     Moor
    0.86
    hyde
    0.76
     McF
    0.75
    tera
    0.74
    hattan
    0.73
    thur
    0.66
    erva
    0.66
    anqu
    0.65
     Buchanan
    0.65
    deals
    0.64
    Activations Density 0.034%

    No Known Activations