© 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. 10-RES-JB
    11. 11024
    Prev
    Next
    INDEX
    Explanations

    names and titles, particularly from news articles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addons
    -0.77
    adas
    -0.75
    units
    -0.72
    cards
    -0.71
    rule
    -0.70
    oths
    -0.70
    hots
    -0.69
    antic
    -0.68
    otin
    -0.67
    blocks
    -0.66
    POSITIVE LOGITS
     Jr
    1.37
     Founder
    1.34
     PhD
    1.27
     Editor
    1.23
     Director
    1.23
     Managing
    1.23
     MD
    1.21
     CEO
    1.18
     founder
    1.15
     VP
    1.15
    Activations Density 0.165%

    No Known Activations