© 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. 4-RES-JB
    11. 14812
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Peña" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    the letter "a" in various contexts and combinations

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

    No Comments

    Negative Logits
    schild
    -0.94
    ailability
    -0.87
     tremend
    -0.71
     dividends
    -0.69
     finalists
    -0.66
    usercontent
    -0.65
     Squid
    -0.63
    ģ«
    -0.62
    utenberg
    -0.61
     Beacon
    -0.60
    POSITIVE LOGITS
     Nieto
    1.03
    chio
    0.78
    illin
    0.75
    anski
    0.74
    utor
    0.73
    jong
    0.72
    asus
    0.71
    ciating
    0.68
     Citation
    0.67
    phe
    0.66
    Activations Density 0.146%

    No Known Activations