© 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. 8-RES-JB
    11. 4608
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to products or media items

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to products, media, and recreational substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ·ãĥ£
    -0.67
     Dhabi
    -0.63
     corners
    -0.56
    inas
    -0.56
    è¦
    -0.56
    ĪĴ
    -0.55
    ãĤ«
    -0.53
    lap
    -0.50
     clauses
    -0.50
    Ŀ
    -0.49
    POSITIVE LOGITS
     anew
    0.91
     aloud
    0.90
     anonymously
    0.88
     safely
    0.86
     responsibly
    0.85
     toget
    0.84
     cheaply
    0.83
     peacefully
    0.83
     orally
    0.82
    washer
    0.80
    Activations Density 0.336%

    No Known Activations