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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 7690
    Prev
    Next
    INDEX
    Explanations

    references to or descriptions of foot-related topics or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to "foot," indicating a focus on details or notes that may be overlooked

    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
    acha
    -0.70
     Learned
    -0.65
    PsyNetMessage
    -0.64
     Parenthood
    -0.64
     RAND
    -0.63
    ALD
    -0.63
     Downs
    -0.62
    anyahu
    -0.61
    ÃĥÃĤ
    -0.59
    ³
    -0.58
    POSITIVE LOGITS
    notes
    1.17
    bridge
    1.14
    prints
    1.12
    falls
    1.09
    steps
    1.07
    step
    1.05
    wear
    1.03
    path
    1.02
    fall
    0.98
    print
    0.96
    Activations Density 0.036%

    No Known Activations