© 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. 7714
    Prev
    Next
    INDEX
    Explanations

    words related to education and academic terms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to glycine and tuition

    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
    sonian
    -0.76
    erness
    -0.74
     ot
    -0.68
    Score
    -0.67
     Fisheries
    -0.65
    yu
    -0.65
     Robot
    -0.65
    aday
    -0.65
    rer
    -0.64
    olphin
    -0.63
    POSITIVE LOGITS
    uate
    1.00
    uates
    0.90
    ohydrate
    0.84
    anwhile
    0.81
    TABLE
    0.79
    esville
    0.78
    uated
    0.78
     grease
    0.76
    uating
    0.73
    uations
    0.72
    Activations Density 0.078%

    No Known Activations