© 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. 8-RES-JB
    11. 7702
    Prev
    Next
    INDEX
    Explanations

    specific numerical references or mentions

    oai_token-act-pair · gpt-3.5-turbo

    multiple occurrences or mentions of the number 13

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iques
    -0.67
     tremend
    -0.66
    ierrez
    -0.66
    anamo
    -0.65
    gart
    -0.64
    spread
    -0.61
    rique
    -0.60
     belly
    -0.60
    ause
    -0.60
    assetsadobe
    -0.59
    POSITIVE LOGITS
    66
    0.96
     Reasons
    0.95
    37
    0.91
    rd
    0.90
    87
    0.88
    94
    0.87
    71
    0.85
    76
    0.85
    77
    0.84
    73
    0.83
    Activations Density 0.039%

    No Known Activations