© 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. 10-RES-JB
    11. 11138
    Prev
    Next
    INDEX
    Explanations

    arguments or perspectives put forth in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that present arguments or counterarguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fecture
    -0.71
     Volunte
    -0.70
     naughty
    -0.66
     Niño
    -0.66
     Transition
    -0.65
     Monitoring
    -0.64
     destiny
    -0.64
     superv
    -0.62
     Nurs
    -0.62
    Sync
    -0.62
    POSITIVE LOGITS
     arguments
    1.48
    argument
    1.41
     argument
    1.40
     Argument
    1.36
     arguing
    1.33
    Arg
    1.31
     rebutt
    1.30
     convinc
    1.23
     persuasive
    1.20
     refute
    1.19
    Activations Density 0.369%

    No Known Activations