© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2869
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or topics mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reference" and its variations

    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
    eous
    -0.75
    lymp
    -0.75
    byss
    -0.72
    moil
    -0.70
    ighty
    -0.66
    iless
    -0.65
    manship
    -0.64
     Dragonbound
    -0.62
    UX
    -0.62
    xit
    -0.62
    POSITIVE LOGITS
     reference
    4.07
    reference
    2.53
     references
    2.45
     Reference
    2.40
    Reference
    1.92
     referencing
    1.85
     References
    1.61
     referenced
    1.60
     refer
    1.58
     mention
    1.46
    Activations Density 0.014%

    No Known Activations