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. 3-RES-JB
    6. 19180
    Prev
    Next
    INDEX
    Explanations

    patterned sequences of miscellaneous characters

    oai_token-act-pair · gpt-3.5-turbo

    unusual characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folk
    -0.88
    abase
    -0.78
     tampering
    -0.74
     breathing
    -0.73
    geries
    -0.72
     swall
    -0.71
     fragmentation
    -0.69
     nursery
    -0.69
     fragmented
    -0.67
     migr
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.43
    ï¸
    1.16
    âĶĢâĶĢâĶĢâĶĢ
    1.04
    âĸł
    0.93
    âĶĢ
    0.92
    ł
    0.91
    VERTISEMENT
    0.87
    ĺ
    0.86
    âĸ
    0.85
    ¯
    0.84
    Activations Density 0.030%

    No Known Activations