© 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 EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 2903
    Prev
    Next
    INDEX
    Explanations

    terms with the suffix '-ista', which could be related to occupations or ideologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of specialists or experts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fish
    -0.68
    glers
    -0.66
    MENTS
    -0.65
     Norse
    -0.65
    brother
    -0.63
    lying
    -0.63
    sub
    -0.63
    eric
    -0.63
    tra
    -0.62
    relations
    -0.62
    POSITIVE LOGITS
    ista
    1.33
    istas
    1.22
    terday
    0.83
    llan
    0.79
    ignt
    0.78
    ea
    0.77
    uto
    0.75
     Libre
    0.75
    yip
    0.74
    uthor
    0.74
    Activations Density 0.010%

    No Known Activations