© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9257
    Prev
    Next
    INDEX
    Explanations

    mentions of famous musicians or public personalities named Mozart, Kozinski, Rogen, or Lieberman

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities related to music or arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yard
    -0.65
     Scandinavian
    -0.63
     contrasting
    -0.62
     Lobby
    -0.61
    ACTED
    -0.60
     Scots
    -0.59
     comparable
    -0.58
    riott
    -0.58
     Pax
    -0.57
     Celtic
    -0.57
    POSITIVE LOGITS
    ymes
    1.13
    hou
    1.08
    ombie
    1.06
    hao
    1.01
    eki
    1.00
    illa
    0.98
    illas
    0.97
    akura
    0.93
    enegger
    0.93
    arella
    0.93
    Activations Density 0.035%

    No Known Activations