© 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. 1-RES-JB
    11. 16360
    Prev
    Next
    INDEX
    Explanations

    the number "three" mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "three."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isky
    -0.64
    agate
    -0.62
    rolet
    -0.61
     Congratulations
    -0.60
    igation
    -0.60
    IAS
    -0.58
    UGE
    -0.57
    utable
    -0.57
    igate
    -0.56
    osate
    -0.56
    POSITIVE LOGITS
    teenth
    1.17
    teen
    1.16
    peat
    1.09
    rd
    1.00
    fif
    0.98
    thirds
    0.96
     quarters
    0.93
    aciously
    0.92
    een
    0.92
     consecutive
    0.91
    Activations Density 0.056%

    No Known Activations