© 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. 15311
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rap" at varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rap" in various contexts

    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
     wills
    -0.75
     Takeru
    -0.67
    bright
    -0.63
     Mississ
    -0.62
     recall
    -0.62
     Jong
    -0.59
     Schwarz
    -0.59
     Lauder
    -0.58
     Garg
    -0.58
    natureconservancy
    -0.58
    POSITIVE LOGITS
    odcast
    1.15
    rap
    1.09
    hene
    0.96
    olitics
    0.94
    heny
    0.94
    artisan
    0.89
    ixel
    0.88
    inion
    0.87
    ascal
    0.86
    oline
    0.85
    Activations Density 0.007%

    No Known Activations