© 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. 8-RES-JB
    11. 11470
    Prev
    Next
    INDEX
    Explanations

    references related to famous personalities or characters

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to people involved in incidents or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dashed
    -0.58
     urgency
    -0.56
     novelty
    -0.53
     ribbon
    -0.52
     irony
    -0.52
     confidential
    -0.52
     appointment
    -0.50
     migration
    -0.50
     transition
    -0.50
     rat
    -0.49
    POSITIVE LOGITS
    Corp
    0.82
    opia
    0.73
    ukong
    0.71
    opa
    0.69
    idae
    0.68
    oks
    0.66
    ault
    0.66
    ax
    0.66
    omon
    0.66
    ak
    0.65
    Activations Density 0.476%

    No Known Activations