© 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. 16661
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles and professional roles

    oai_token-act-pair · gpt-3.5-turbo

    financial terms and statistics related to economic or organizational contexts

    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
     juggling
    -0.64
     hampered
    -0.58
     mutants
    -0.58
     gradual
    -0.58
     germ
    -0.58
     frail
    -0.58
     entangled
    -0.56
     haunted
    -0.56
     fitness
    -0.56
     stretches
    -0.56
    POSITIVE LOGITS
    >.
    1.52
    *.
    1.51
    +.
    1.51
    `.
    1.51
    %.
    1.48
    '.
    1.47
    _.
    1.44
    $.
    1.44
    .).
    1.44
    ''.
    1.39
    Activations Density 0.586%

    No Known Activations