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. 8-RES-JB
    6. 4338
    Prev
    Next
    INDEX
    Explanations

    instances of slipping or sliding

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slip" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nda
    -0.70
    è¦ļéĨĴ
    -0.70
    ============
    -0.68
    rises
    -0.65
    ========
    -0.64
    Export
    -0.62
    ¯¯
    -0.59
    da
    -0.58
    nea
    -0.56
    ãĥ£
    -0.56
    POSITIVE LOGITS
    stream
    0.93
     away
    0.90
     Away
    0.83
     into
    0.78
    otom
    0.78
    weed
    0.77
    rift
    0.77
    eki
    0.76
    away
    0.76
     INTO
    0.75
    Activations Density 0.026%

    No Known Activations