© 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. 11-RES-JB
    11. 19314
    Prev
    Next
    INDEX
    Explanations

    titles or roles in organizations

    oai_token-act-pair · gpt-3.5-turbo

    job titles or positions of authority

    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
    TIME
    -0.64
    idden
    -0.57
     Fighters
    -0.56
    azes
    -0.55
     è£ıç
    -0.55
     Witches
    -0.54
    lez
    -0.54
    IRE
    -0.54
     Soldiers
    -0.53
    à¨
    -0.53
    POSITIVE LOGITS
     overseeing
    0.84
     extraord
    0.83
     responsible
    0.81
    inator
    0.77
     liaison
    0.75
     specializing
    0.75
    iliate
    0.74
     emer
    0.72
     negotiator
    0.72
     laureate
    0.70
    Activations Density 0.159%

    No Known Activations