© 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. 7885
    Prev
    Next
    INDEX
    Explanations

    contrasting or qualifying terms in a statement

    oai_token-act-pair · gpt-3.5-turbo

    the word "albeit" and its variations in context

    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
     Gates
    -0.61
     Applications
    -0.59
     departments
    -0.59
     Specific
    -0.58
    arks
    -0.56
     Related
    -0.54
     Special
    -0.54
     Irving
    -0.53
     specified
    -0.53
     Statistics
    -0.53
    POSITIVE LOGITS
     albeit
    2.69
    albeit
    2.37
    living
    1.16
    acet
    0.96
    though
    0.92
     nonetheless
    0.85
    although
    0.84
     viz
    0.84
     namely
    0.82
    beit
    0.81
    Activations Density 0.015%

    No Known Activations