© 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. 1-RES-JB
    11. 5457
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiation or agreement

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herent
    -0.53
     predec
    -0.50
    sylv
    -0.48
     oxide
    -0.46
    Override
    -0.46
    estones
    -0.46
    inately
    -0.45
    athered
    -0.44
    stal
    -0.44
    rench
    -0.43
    POSITIVE LOGITS
     albeit
    0.72
     although
    0.67
     Kinnikuman
    0.67
     however
    0.63
     huh
    0.60
     meanwhile
    0.59
    apa
    0.59
     though
    0.57
     namely
    0.56
     moreover
    0.56
    Activations Density 1.154%

    No Known Activations