© 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. 11-RES-JB
    11. 17124
    Prev
    Next
    INDEX
    Explanations

    numerical and special characters within a structured format

    oai_token-act-pair · gpt-3.5-turbo

    symbols and numeric values associated with ranking or data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     357
    -0.78
    hower
    -0.78
     356
    -0.75
    rill
    -0.75
     402
    -0.74
     292
    -0.73
    sonian
    -0.73
     361
    -0.72
    ocument
    -0.72
    572
    -0.70
    POSITIVE LOGITS
    14
    1.29
    13
    1.27
     14
    1.01
    139
    1.00
     13
    0.96
    15
    0.88
    134
    0.88
    130
    0.87
    138
    0.84
    140
    0.82
    Activations Density 0.072%

    No Known Activations