© 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. 601
    Prev
    Next
    INDEX
    Explanations

    the syllable "ico" within words

    oai_token-act-pair · gpt-4-turbo

    phrases related to individuals with the name "Federico"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'ico' as a suffix or in various contexts

    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
    gling
    -0.73
    said
    -0.73
    LESS
    -0.72
    topic
    -0.72
    mable
    -0.70
    subject
    -0.67
    ĸļ
    -0.67
    represent
    -0.65
    birds
    -0.65
    lihood
    -0.65
    POSITIVE LOGITS
    ico
    0.90
    entric
    0.85
    emia
    0.83
    verage
    0.81
    agate
    0.80
    ffee
    0.80
    zzi
    0.79
    onduct
    0.78
    cia
    0.77
    leans
    0.77
    Activations Density 0.006%

    No Known Activations