© 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. 7-RES-JB
    11. 13396
    Prev
    Next
    INDEX
    Explanations

    specific strings of special characters interleaved with letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-alphanumeric symbols in the text

    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
     silhou
    -0.81
    ocating
    -0.67
     ancest
    -0.66
     juggling
    -0.65
    ENTS
    -0.63
    ocation
    -0.62
    oted
    -0.62
    puff
    -0.62
     contrace
    -0.60
     propel
    -0.59
    POSITIVE LOGITS
    vre
    0.96
    hyde
    0.93
    gypt
    0.86
    ï
    0.85
    Ħ¢
    0.82
    ¼
    0.81
    rica
    0.80
    ç
    0.79
    Ëľ
    0.79
    bia
    0.78
    Activations Density 0.007%

    No Known Activations