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. 2-RES-JB
    6. 142
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'reference'

    oai_token-act-pair · gpt-4-turbo

    references to specific items, concepts, or people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awk
    -0.75
    ihad
    -0.74
    alach
    -0.70
    Ģ
    -0.69
    isine
    -0.66
    onew
    -0.66
    ailability
    -0.66
    ¯¯¯¯
    -0.65
    cffff
    -0.65
    omew
    -0.65
    POSITIVE LOGITS
     Reference
    0.94
    reference
    0.92
     reference
    0.83
     references
    0.83
    Reference
    0.77
    enza
    0.72
     Implementation
    0.70
    ogue
    0.69
    minist
    0.69
     References
    0.68
    Activations Density 0.010%

    No Known Activations