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. 6-RES-JB
    6. 1894
    Prev
    Next
    INDEX
    Explanations

    the word "rack" followed by a number indicating a level of accumulation or organization

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rack" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Austral
    -0.69
    éĸ
    -0.67
    iating
    -0.64
     Kabul
    -0.61
    iations
    -0.58
     Pione
    -0.58
    ulton
    -0.57
    orescence
    -0.57
    itars
    -0.57
     ÎĶ
    -0.57
    POSITIVE LOGITS
    acks
    1.00
    washer
    0.97
    cloth
    0.96
     racks
    0.96
    ings
    0.95
    yard
    0.92
     rack
    0.92
    ety
    0.91
    mount
    0.86
     Rack
    0.85
    Activations Density 0.019%

    No Known Activations