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. 18060
    Prev
    Next
    INDEX
    Explanations

    words related to constraints or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    the word "constant" or its variations in different 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
    cules
    -0.77
    pmwiki
    -0.76
     nerv
    -0.73
    bones
    -0.71
    dos
    -0.67
    ward
    -0.66
    jong
    -0.65
    ombies
    -0.64
    byss
    -0.64
    WARE
    -0.64
    POSITIVE LOGITS
    ellation
    1.41
    ipation
    1.37
    abulary
    1.33
    expr
    1.20
    itution
    1.19
    ricted
    1.10
    rast
    1.09
    ricting
    1.09
    rict
    1.08
    riction
    1.07
    Activations Density 0.024%

    No Known Activations