© 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. 4049
    Prev
    Next
    INDEX
    Explanations

    news-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    the term "READ" followed by a call to action or further engagement

    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
     eleg
    -0.69
     strat
    -0.67
     humor
    -0.64
     harm
    -0.63
     neutral
    -0.63
     Chase
    -0.63
     intrusion
    -0.62
     premium
    -0.60
     induction
    -0.60
     Cantor
    -0.59
    POSITIVE LOGITS
    READ
    4.33
    WATCH
    1.86
     READ
    1.84
    read
    1.75
    SPONSORED
    1.68
    RELATED
    1.65
    Read
    1.63
    reads
    1.57
    reading
    1.49
    VIDEO
    1.49
    Activations Density 0.010%

    No Known Activations