© 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. 9999
    Prev
    Next
    INDEX
    Explanations

    numeric values within a structured text

    oai_token-act-pair · gpt-3.5-turbo

    elements related to sequences, organized data, or statistical information

    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
    ï¸
    -0.75
     morp
    -0.66
    ipeg
    -0.66
     aggregation
    -0.63
     Cipher
    -0.63
    byss
    -0.61
    Tes
    -0.60
     cul
    -0.60
    unts
    -0.60
    aspers
    -0.60
    POSITIVE LOGITS
    12
    0.98
    Ö¼
    0.97
     12
    0.91
     122
    0.88
    122
    0.83
    1200
    0.82
     42
    0.79
     118
    0.77
     62
    0.76
     twelve
    0.76
    Activations Density 0.069%

    No Known Activations