© 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. 7-RES-JB
    11. 13532
    Prev
    Next
    INDEX
    Explanations

    unintelligible or garbled text

    oai_token-act-pair · gpt-3.5-turbo

    unusual or non-standard characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nationals
    -0.55
     Forums
    -0.53
     Gazette
    -0.50
     Tours
    -0.50
     Lynn
    -0.49
     unanimously
    -0.49
     Drag
    -0.48
     toured
    -0.47
     signs
    -0.47
     Santiago
    -0.47
    POSITIVE LOGITS
    matical
    0.73
    itu
    0.68
    edo
    0.66
    vious
    0.65
    plet
    0.65
    dden
    0.64
    matic
    0.63
    erous
    0.63
    igible
    0.62
    cious
    0.62
    Activations Density 0.631%

    No Known Activations