© 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. 0-RES-JB
    11. 11615
    Prev
    Next
    INDEX
    Explanations

    references to actions or discussions done in private

    oai_token-act-pair · gpt-3.5-turbo

    references to private ownership and private matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    action
    -0.66
     relevance
    -0.65
     sweeps
    -0.65
    asion
    -0.64
    omen
    -0.61
    lime
    -0.61
    awed
    -0.61
    assic
    -0.60
     kicks
    -0.60
    ity
    -0.59
    POSITIVE LOGITS
     privately
    3.98
     publicly
    2.03
     private
    1.76
     anonymously
    1.60
    private
    1.42
    Private
    1.41
     openly
    1.38
     secretly
    1.37
     internally
    1.34
     Private
    1.25
    Activations Density 0.024%

    No Known Activations