© 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. 8126
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning various topics or items

    oai_token-act-pair · gpt-3.5-turbo

    the word "mention" or its variations in the context of discussing topics or subjects

    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
    ourge
    -0.66
    wr
    -0.66
    Op
    -0.63
    oot
    -0.63
    normal
    -0.61
     ..........
    -0.60
    pir
    -0.59
    etr
    -0.58
    flows
    -0.56
    np
    -0.56
    POSITIVE LOGITS
     mention
    3.89
     mentions
    2.55
     mentioning
    2.35
     mentioned
    1.63
    mentioned
    1.43
     reference
    1.39
     cite
    1.36
     remark
    1.23
     praise
    1.17
     references
    1.17
    Activations Density 0.012%

    No Known Activations