© 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. 9-RES-JB
    11. 3762
    Prev
    Next
    INDEX
    Explanations

    prohibitions or restrictions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hindsight
    -0.82
     actu
    -0.75
     Lyndon
    -0.71
     optimistic
    -0.71
     mirac
    -0.70
     aw
    -0.69
     fab
    -0.68
     retrospect
    -0.66
    issance
    -0.66
    ritic
    -0.65
    POSITIVE LOGITS
     prohibit
    1.24
     prohibited
    1.23
     prohibitions
    1.20
     prohibits
    1.19
     forbids
    1.19
    iquette
    1.18
     forbid
    1.11
     nudity
    1.11
     curfew
    1.04
     tresp
    1.02
    Activations Density 0.709%

    No Known Activations