© 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. 8-RES-JB
    11. 6243
    Prev
    Next
    INDEX
    Explanations

    activations related to political terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "P"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adm
    -0.76
     susp
    -0.69
    ģĸ
    -0.69
     diplom
    -0.68
     Aval
    -0.67
     Pry
    -0.67
     phyl
    -0.66
     wip
    -0.65
     differe
    -0.65
     transports
    -0.64
    POSITIVE LOGITS
    redict
    1.39
    ossible
    1.35
    ossession
    1.28
    aired
    1.25
    ractical
    1.21
    ossibly
    1.20
    odcast
    1.20
    overty
    1.19
    ierce
    1.18
    ardon
    1.18
    Activations Density 0.056%

    No Known Activations