© 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. 19505
    Prev
    Next
    INDEX
    Explanations

    the word "Ant" followed by a single digit, likely looking for specific references to the term "Ant" with a numerical identifier

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "Ant" followed by additional characters or context-related terms

    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
    UTION
    -0.98
    FORMATION
    -0.83
    ESSION
    -0.78
    =-=-=-=-
    -0.73
    OURCE
    -0.72
    )=(
    -0.72
    UGE
    -0.71
    wagen
    -0.71
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    SIGN
    -0.70
    POSITIVE LOGITS
    oine
    1.02
    enna
    0.99
    agonists
    0.98
    agonist
    0.97
    acid
    0.96
    idepress
    0.95
    heon
    0.93
    rop
    0.93
    elope
    0.93
    ioxid
    0.92
    Activations Density 0.010%

    No Known Activations