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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1994
    Prev
    Next
    INDEX
    Explanations

    sentences containing the structure "All [subject] do is [verb]"

    oai_token-act-pair · gpt-3.5-turbo

    directives or instructions related to actions and behaviors

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

    No Comments

    Negative Logits
    ahime
    -0.78
    edia
    -0.73
    nect
    -0.67
    itor
    -0.64
    uci
    -0.64
    iti
    -0.64
     spiked
    -0.63
    prus
    -0.63
     Prel
    -0.61
     Acceler
    -0.60
    POSITIVE LOGITS
     except
    1.32
    except
    1.01
     imaginable
    0.97
     besides
    0.88
     nodd
    0.80
     mathemat
    0.78
     conceivable
    0.74
     ensu
    0.74
     toget
    0.73
     equally
    0.71
    Activations Density 0.699%

    No Known Activations