© 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. 642
    Prev
    Next
    INDEX
    Explanations

    the name "Sonia"

    oai_token-act-pair · gpt-4-turbo

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with significant events or roles

    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
    acement
    -0.91
    ãģ¦
    -0.84
    sonian
    -0.81
    enegger
    -0.80
    oster
    -0.78
    estern
    -0.77
    aber
    -0.77
    ledge
    -0.77
    essors
    -0.77
    ships
    -0.73
    POSITIVE LOGITS
    cles
    0.82
    Files
    0.81
     Kush
    0.77
    Reviewer
    0.75
     Sonia
    0.73
     Archdemon
    0.73
     Abedin
    0.73
     è£ıè
    0.70
    vation
    0.70
    ENC
    0.69
    Activations Density 0.022%

    No Known Activations