© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16528
    Prev
    Next
    INDEX
    Explanations

    the concept of "separation" or "division" related to different contexts such as law, government, relationships, and physical space

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paw
    -0.77
     Gundam
    -0.67
    gob
    -0.66
    ourced
    -0.65
    bold
    -0.64
    oots
    -0.64
     Myst
    -0.64
     Pants
    -0.63
     Sporting
    -0.62
     favourites
    -0.62
    POSITIVE LOGITS
     separation
    4.12
     separ
    1.93
     separating
    1.83
    separ
    1.71
     separated
    1.64
     breakup
    1.55
     isolation
    1.36
     independence
    1.34
     segregation
    1.33
     separates
    1.32
    Activations Density 0.014%

    No Known Activations