Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 14861
    Prev
    Next
    INDEX
    Explanations

    words related to expertise or proficiency

    oai_token-act-pair · gpt-3.5-turbo

    references to avarice and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adoption
    -0.59
     shortened
    -0.59
     waivers
    -0.59
     Dempsey
    -0.58
     mine
    -0.57
     Guys
    -0.57
    Companies
    -0.56
     Korea
    -0.56
     Bridge
    -0.55
     charging
    -0.55
    POSITIVE LOGITS
    icidal
    1.06
    acious
    1.03
    olitical
    1.03
    iological
    0.99
    hemer
    0.99
    iotic
    0.95
    entious
    0.94
    irtual
    0.93
    urable
    0.93
    itudinal
    0.92
    Activations Density 0.182%

    No Known Activations