© 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. 2-RES-JB
    6. 918
    Prev
    Next
    INDEX
    Explanations

    the sequence "Sev"

    oai_token-act-pair · gpt-4-turbo

    proper nouns or names related to a specific entity, potentially a person or a place named Sev

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or organizations

    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
    matically
    -0.71
    ammy
    -0.68
    paced
    -0.64
     cane
    -0.64
    braska
    -0.63
    road
    -0.62
     Warren
    -0.62
    shadow
    -0.61
    advertising
    -0.60
    esity
    -0.60
    POSITIVE LOGITS
     Sev
    1.01
    chenko
    0.98
    itri
    0.96
    illa
    0.90
    iour
    0.89
    anches
    0.87
    illo
    0.82
    opol
    0.81
    apor
    0.78
    ius
    0.78
    Activations Density 0.010%

    No Known Activations