Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2261
    Prev
    Next
    INDEX
    Explanations

    specific parts or sections of text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific "parts" or sections of various contexts

    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
    berus
    -0.79
    ãĤī
    -0.67
     Skies
    -0.67
    ctr
    -0.65
     shorts
    -0.63
     Predators
    -0.61
    ministic
    -0.61
    culosis
    -0.60
     cumbers
    -0.60
     commissions
    -0.60
    POSITIVE LOGITS
    ials
    0.97
    ridges
    0.91
    meal
    0.90
    ridge
    0.87
    icular
    0.81
    icularly
    0.76
    uring
    0.75
    ners
    0.74
    aking
    0.73
    dated
    0.71
    Activations Density 0.042%

    No Known Activations