© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    patterns with a prefix "re-" followed by another word or letters indicating a possible action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "re-" in words

    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
     Relief
    -0.75
     Grade
    -0.71
     vast
    -0.69
     die
    -0.69
     percentile
    -0.68
     relief
    -0.67
     feared
    -0.66
     SHARES
    -0.66
     Slater
    -0.64
     PIT
    -0.64
    POSITIVE LOGITS
    introdu
    1.61
    elected
    1.44
    tool
    1.44
    examination
    1.43
    establish
    1.42
    eval
    1.42
    entry
    1.40
    election
    1.39
    imag
    1.36
    adjust
    1.35
    Activations Density 0.029%

    No Known Activations