© 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. 12811
    Prev
    Next
    INDEX
    Explanations

    words related to arguments or debates

    oai_token-act-pair · gpt-3.5-turbo

    references to logical or rhetorical arguments

    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
     Carbuncle
    -0.69
    ISTER
    -0.63
    idays
    -0.62
     Atomic
    -0.62
    lights
    -0.62
     PHOTO
    -0.61
    ookie
    -0.60
     unmarked
    -0.60
    aches
    -0.60
    ardy
    -0.59
    POSITIVE LOGITS
    ative
    1.30
    uments
    1.14
     against
    1.05
    abl
    1.03
    ument
    0.99
    ation
    0.92
    ator
    0.91
     arguments
    0.88
    atives
    0.88
    atively
    0.85
    Activations Density 0.040%

    No Known Activations