© 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. 7-RES-JB
    11. 6510
    Prev
    Next
    INDEX
    Explanations

    political or controversial statements or decisions made by individuals or administrations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of public reaction to political decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceae
    -0.78
     remembers
    -0.58
     solvent
    -0.57
     pled
    -0.57
     Prediction
    -0.57
     Ops
    -0.56
     utmost
    -0.56
    verbs
    -0.54
     depends
    -0.54
     resides
    -0.54
    POSITIVE LOGITS
    nesty
    0.77
    neau
    0.72
     portray
    0.68
     inaccur
    0.68
     DeVos
    0.66
     insin
    0.66
    amation
    0.65
     lack
    0.65
     criticisms
    0.64
     encro
    0.64
    Activations Density 0.679%

    No Known Activations