© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1986
    Prev
    Next
    INDEX
    Explanations

    instances of extreme descriptions or emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong negative or positive opinion, particularly emphasizing the word "so."

    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
     Flavoring
    -0.77
    theless
    -0.71
    nings
    -0.70
    works
    -0.70
    work
    -0.68
     eviction
    -0.65
    Afee
    -0.65
    amac
    -0.63
    ership
    -0.63
     excerpts
    -0.62
    POSITIVE LOGITS
    oooo
    1.25
    ooo
    1.24
    bered
    1.23
    oths
    1.11
    oooooooo
    1.10
     far
    1.01
     much
    0.98
    apy
    0.98
    oooooooooooooooo
    0.95
    othes
    0.91
    Activations Density 0.083%

    No Known Activations