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. 18938
    Prev
    Next
    INDEX
    Explanations

    articles or news reports

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stories" along with various contexts related to news and reports

    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
    viation
    -0.77
    orde
    -0.63
    viks
    -0.61
    oÄŁ
    -0.61
    alties
    -0.59
    alty
    -0.59
    mented
    -0.59
    eering
    -0.56
    bler
    -0.56
    arity
    -0.55
    POSITIVE LOGITS
    hots
    0.87
    pace
    0.72
    ource
    0.68
    ilo
    0.64
    icle
    0.64
     involving
    0.64
     quoting
    0.60
     trending
    0.60
    pection
    0.60
    peed
    0.60
    Activations Density 0.041%

    No Known Activations