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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 6184
    Prev
    Next
    INDEX
    Explanations

    measurement units related to speed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements of time or speed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agles
    -0.73
    ATHER
    -0.72
    roots
    -0.72
    Paper
    -0.68
    »Ĵ
    -0.67
    XY
    -0.67
    irie
    -0.66
    Marginal
    -0.66
    Steel
    -0.64
    USS
    -0.64
    POSITIVE LOGITS
     baseman
    0.93
     glance
    0.88
    ngth
    0.80
    aneously
    0.78
    aries
    0.74
     burst
    0.72
     Listen
    0.70
     elapsed
    0.70
    fps
    0.68
     harmonic
    0.68
    Activations Density 0.023%

    No Known Activations