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. 0-RES-JB
    6. 7241
    Prev
    Next
    INDEX
    Explanations

    references to the location "Abercynon"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "non-" indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charts
    -0.75
     bow
    -0.71
     scene
    -0.67
     stacks
    -0.66
     sooner
    -0.66
     height
    -0.64
     promise
    -0.64
     yards
    -0.63
     precip
    -0.63
     towers
    -0.62
    POSITIVE LOGITS
    non
    3.89
    Non
    2.21
     NON
    1.66
     Non
    1.66
     non
    1.48
    no
    1.43
    nan
    1.20
    nos
    1.17
    anti
    1.14
    not
    1.10
    Activations Density 0.013%

    No Known Activations