© 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
    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. 1060
    Prev
    Next
    INDEX
    Explanations

    answers to questions or prompts

    oai_token-act-pair · gpt-3.5-turbo

    references to providing answers or responses

    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
    Lago
    -0.58
     caps
    -0.57
    ãĤ§
    -0.55
    older
    -0.55
    erial
    -0.55
    redits
    -0.55
     Purch
    -0.54
    lav
    -0.54
     staged
    -0.54
     Beaut
    -0.54
    POSITIVE LOGITS
     answer
    4.03
     answers
    2.80
    answer
    2.75
     Answer
    2.69
    Answer
    2.49
     answering
    2.28
     answered
    2.26
     reply
    2.25
     answ
    1.90
     Answers
    1.84
    Activations Density 0.015%

    No Known Activations