© 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. 2-RES-JB
    11. 12161
    Prev
    Next
    INDEX
    Explanations

    numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical identifiers or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.91
    skirts
    -0.89
     tiss
    -0.88
    ¥ŀ
    -0.88
    achus
    -0.86
    nesday
    -0.86
     unden
    -0.80
     tradem
    -0.79
     ende
    -0.78
    purpose
    -0.78
    POSITIVE LOGITS
     ILCS
    0.96
    MHz
    0.92
    328
    0.89
    67
    0.84
    68
    0.84
    00
    0.80
    75
    0.78
    69
    0.77
     MHz
    0.77
    317
    0.74
    Activations Density 0.025%

    No Known Activations