© 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. 4-RES-JB
    11. 3603
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers that often appear in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 65 in various contexts

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

    No Comments

    Negative Logits
    mble
    -0.85
    nesday
    -0.78
    ettings
    -0.76
    yers
    -0.72
    hops
    -0.71
    pressure
    -0.71
    yang
    -0.70
    cliffe
    -0.69
    iya
    -0.68
    apeake
    -0.67
    POSITIVE LOGITS
     ILCS
    1.47
    328
    1.08
    ENCY
    0.89
    ONT
    0.87
    467
    0.85
    625
    0.83
    65
    0.82
    630
    0.81
    765
    0.81
    ENC
    0.77
    Activations Density 0.026%

    No Known Activations