© 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. 3752
    Prev
    Next
    INDEX
    Explanations

    statements from various sources, such as spokespersons, on a given subject

    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
     temptation
    -0.72
     chopping
    -0.71
     deduction
    -0.71
     steroids
    -0.70
     indifferent
    -0.70
    bably
    -0.70
     escaping
    -0.69
     fodder
    -0.69
     killer
    -0.68
     deductions
    -0.68
    POSITIVE LOGITS
    Statement
    1.24
    Dear
    1.23
    Our
    1.10
    Effective
    1.09
    Regarding
    1.05
    We
    1.01
    Hi
    1.00
    Thank
    0.98
    Correct
    0.96
    Hello
    0.93
    Activations Density 0.125%

    No Known Activations