© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13061
    Prev
    Next
    INDEX
    Explanations

    bombings or explosive events in urban areas with similar naming conventions, such as the word "ember" being present in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ember" and its variations, indicating a focus on time references related to the month of December

    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
    andra
    -0.82
    ively
    -0.78
    SPONSORED
    -0.77
    arella
    -0.75
    hiba
    -0.74
    oms
    -0.72
    omen
    -0.70
    est
    -0.69
    esthesia
    -0.68
    omal
    -0.68
    POSITIVE LOGITS
    utive
    0.97
    theless
    0.88
    gence
    0.87
    utical
    0.86
    getic
    0.86
    ãĤ¡
    0.84
    deen
    0.79
    nesday
    0.77
    ERAL
    0.75
    ulkan
    0.74
    Activations Density 0.023%

    No Known Activations