© 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. 9736
    Prev
    Next
    INDEX
    Explanations

    proper nouns or brand names, specifically related to a brand or entity named "Gir"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Gir" and its variations, as well as references to a specific product or entity labeled "DG."

    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
     Samoa
    -0.76
    ãĥ¼ãĥĨ
    -0.75
    ãĥĩãĤ£
    -0.74
     Contra
    -0.69
     Archdemon
    -0.64
    使
    -0.63
    ACTED
    -0.63
    ãĥ¼ãĥ³
    -0.61
    ãĤ¦
    -0.59
     Âł Âł
    -0.59
    POSITIVE LOGITS
    affe
    1.16
    oux
    0.95
    vana
    0.95
    aldi
    0.94
    rier
    0.90
    onda
    0.86
    kees
    0.85
    acha
    0.83
    bour
    0.81
    aval
    0.80
    Activations Density 0.009%

    No Known Activations