© 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. 0-RES-JB
    11. 5269
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to praise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "exactly" and variants of "excellent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     travellers
    -0.67
    kees
    -0.66
     chiefs
    -0.65
     organisers
    -0.64
    åľ
    -0.63
    Tel
    -0.62
     plaque
    -0.60
     holders
    -0.60
     councils
    -0.60
     winds
    -0.59
    POSITIVE LOGITS
    cellent
    2.60
    actly
    2.58
    enstein
    2.25
     Contra
    1.49
    imus
    1.34
    spin
    1.27
    ilver
    1.23
    abre
    1.21
    cakes
    1.10
    iru
    1.07
    Activations Density 0.050%

    No Known Activations