© 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. 10-RES-JB
    11. 9221
    Prev
    Next
    INDEX
    Explanations

    transactions or interactions involving giving, receiving, trading, betting, or pledging

    oai_token-act-pair · gpt-3.5-turbo

    actions involving giving, receiving, and participating in exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asking
    -0.70
    rection
    -0.65
    terness
    -0.65
    uzz
    -0.63
    among
    -0.63
    rison
    -0.60
     extrad
    -0.60
     Manufacturer
    -0.59
    intendent
    -0.58
    affer
    -0.58
    POSITIVE LOGITS
     themselves
    0.82
     misfortune
    0.66
     their
    0.66
     contrace
    0.65
     THEIR
    0.65
     careers
    0.63
     otherwise
    0.63
     RPGs
    0.63
     abortions
    0.62
     histories
    0.61
    Activations Density 0.346%

    No Known Activations