© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 15738
    Prev
    Next
    INDEX
    Explanations

    companies or organizations named "All" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with collective entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.63
     footnote
    -0.62
     tailor
    -0.62
    eday
    -0.60
    tch
    -0.57
     entire
    -0.57
    Dialogue
    -0.56
     closest
    -0.56
     proverb
    -0.55
    acle
    -0.55
    POSITIVE LOGITS
    iple
    0.76
    ahu
    0.73
    clusive
    0.71
    consuming
    0.70
     alike
    0.68
     Reserved
    0.67
     except
    0.67
     sudden
    0.66
    oots
    0.65
    together
    0.64
    Activations Density 0.096%

    No Known Activations