© 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. 12811
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Stefan" with varying levels of similarity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Stefan."

    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
    BACK
    -0.75
    nces
    -0.69
    rights
    -0.66
    LOAD
    -0.63
    ptive
    -0.63
    lled
    -0.61
    REE
    -0.61
    uably
    -0.60
    inals
    -0.59
    ptives
    -0.59
    POSITIVE LOGITS
     Stefan
    1.05
    stadt
    1.01
    ovic
    0.92
     Stef
    0.77
    etti
    0.76
    apo
    0.75
    acci
    0.74
     Rah
    0.74
    ovich
    0.74
     Matte
    0.71
    Activations Density 0.006%

    No Known Activations