© 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. 18766
    Prev
    Next
    INDEX
    Explanations

    terms related to authority, control, and direct communication

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating completeness or control

    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
    gdala
    -0.80
    soDeliveryDate
    -0.75
     Puzzle
    -0.73
    ccording
    -0.72
    orah
    -0.72
    ramid
    -0.72
    crow
    -0.70
    olate
    -0.70
    undrum
    -0.69
    enario
    -0.69
    POSITIVE LOGITS
     access
    1.36
     instructions
    1.21
     permission
    1.20
     assurances
    1.18
     supervision
    1.16
     guidance
    1.12
     approval
    1.08
     control
    1.07
     permissions
    1.05
     indications
    1.04
    Activations Density 0.205%

    No Known Activations