© 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. 12159
    Prev
    Next
    INDEX
    Explanations

    people's names and their actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of political commentary or discourse

    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
    .–
    -0.81
     badass
    -0.75
     goddamn
    -0.74
     gorge
    -0.74
    conservancy
    -0.72
    ggles
    -0.69
     freaking
    -0.69
    isner
    -0.69
     Blizz
    -0.67
    !]
    -0.67
    POSITIVE LOGITS
     Mr
    2.20
    Mr
    2.01
     Ms
    1.87
     Mrs
    1.71
    Ms
    1.69
    Mrs
    1.53
     ''
    1.14
    Newsletter
    1.14
     Prof
    1.07
     Miss
    1.06
    Activations Density 0.227%

    No Known Activations