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. 0-RES-JB
    6. 21314
    Prev
    Next
    INDEX
    Explanations

    examples of texts citing sources or references

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "citing" or variations of it in a document

    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
    prototype
    -0.65
    inn
    -0.62
    rang
    -0.59
     mischief
    -0.59
     PACK
    -0.58
     Extras
    -0.58
    alis
    -0.57
    bean
    -0.57
    ool
    -0.57
     happen
    -0.57
    POSITIVE LOGITS
     citing
    3.61
     quoting
    2.14
     cited
    1.84
     cite
    1.81
     noting
    1.72
     cites
    1.67
     stating
    1.60
     referencing
    1.58
     alleging
    1.47
     referring
    1.44
    Activations Density 0.016%

    No Known Activations