© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17298
    Prev
    Next
    INDEX
    Explanations

    discussions related to political events and actions

    oai_token-act-pair · gpt-3.5-turbo

    formal declarations or statements of concern

    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
    Luck
    -0.85
     hindsight
    -0.76
    glers
    -0.73
     averages
    -0.73
    got
    -0.72
    Enlarge
    -0.72
    VERTISEMENT
    -0.71
     messing
    -0.70
     gossip
    -0.68
     goof
    -0.68
    POSITIVE LOGITS
     reaff
    1.35
     reiterate
    1.30
     condemns
    1.30
     reiter
    1.29
     hereby
    1.28
     unequivocally
    1.24
     denounce
    1.20
     condemn
    1.16
     proclaim
    1.15
     urge
    1.13
    Activations Density 0.728%

    No Known Activations