© 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. 11-RES-JB
    11. 20983
    Prev
    Next
    INDEX
    Explanations

    information related to people's activities, locations, and relationships

    oai_token-act-pair · gpt-3.5-turbo

    activities and hobbies related to personal leisure and family involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BEFORE
    -0.79
    Invalid
    -0.77
    >[
    -0.77
     sooner
    -0.73
     precedent
    -0.69
     subsequently
    -0.69
     deceived
    -0.69
     earlier
    -0.68
     misled
    -0.68
    wrong
    -0.66
    POSITIVE LOGITS
     hobbies
    1.17
     hobby
    0.99
    natureconservancy
    0.92
     freelance
    0.88
     wife
    0.86
     motto
    0.86
     commute
    0.85
     eclectic
    0.81
     ranch
    0.81
     weekends
    0.80
    Activations Density 0.468%

    No Known Activations