© 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. 8-RES-JB
    11. 4585
    Prev
    Next
    INDEX
    Explanations

    names and biographical information about individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals associated with specific actions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unbeliev
    -0.71
    reating
    -0.69
    ivating
    -0.69
     guiName
    -0.67
    pattern
    -0.65
    urers
    -0.62
    commit
    -0.62
    acceptable
    -0.61
     enticing
    -0.61
    .–
    -0.60
    POSITIVE LOGITS
     herself
    0.83
     stint
    0.73
     unsuccessfully
    0.72
    çīĪ
    0.72
     retiring
    0.72
     )]
    0.72
     oversee
    0.71
     consulted
    0.68
     chaired
    0.68
     pseudonym
    0.68
    Activations Density 0.317%

    No Known Activations