© 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. 6-RES-JB
    11. 24444
    Prev
    Next
    INDEX
    Explanations

    titles of books and critical works

    oai_token-act-pair · gpt-3.5-turbo

    references to titles of books and critical works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cancell
    -0.69
    btn
    -0.69
    fen
    -0.68
    idently
    -0.65
     herself
    -0.63
     phr
    -0.63
    ":[
    -0.63
     needles
    -0.62
    claw
    -0.62
    agara
    -0.62
    POSITIVE LOGITS
     Definitive
    0.98
     Unt
    0.79
     Collection
    0.74
     Strategies
    0.72
     Journey
    0.71
     Emerging
    0.71
     Forgotten
    0.71
     Complete
    0.70
     Gathering
    0.70
     Mechanics
    0.70
    Activations Density 0.067%

    No Known Activations