© 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. 11-RES-JB
    11. 24565
    Prev
    Next
    INDEX
    Explanations

    arguments and counterarguments

    oai_token-act-pair · gpt-3.5-turbo

    arguments related to contested scientific claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.76
     Indust
    -0.75
     Volunte
    -0.73
    scenes
    -0.70
     Overse
    -0.68
     VIP
    -0.67
     Elys
    -0.67
    gallery
    -0.67
     Leban
    -0.66
     Heroes
    -0.65
    POSITIVE LOGITS
     rebutt
    1.49
     refuted
    1.45
     Argument
    1.43
     arguments
    1.43
     refute
    1.39
     argument
    1.39
     dispro
    1.34
    Arg
    1.31
     arguing
    1.31
    argument
    1.29
    Activations Density 0.602%

    No Known Activations