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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 717
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'foot'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of "foot" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.71
    acha
    -0.70
    umbn
    -0.70
     Downs
    -0.69
    ALD
    -0.67
    infeld
    -0.65
     cannabin
    -0.64
    ļéĨĴ
    -0.62
    effective
    -0.62
    IZE
    -0.61
    POSITIVE LOGITS
    notes
    1.22
    bridge
    1.13
    prints
    1.02
    wear
    0.98
    steps
    0.97
    falls
    0.96
    step
    0.96
    note
    0.94
    print
    0.92
    sie
    0.91
    Activations Density 0.040%

    No Known Activations