© 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 EvalsExportsinterp-engineNEWAPI 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. 1221
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a degree of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases and structures centered around the article "a" and the concept of being "an" or "a bit of a" something

    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
    aris
    -0.79
    years
    -0.76
    CTV
    -0.75
    ulously
    -0.74
    iless
    -0.73
    ORTS
    -0.73
    loads
    -0.73
    aturday
    -0.72
    ultimate
    -0.72
    enaries
    -0.71
    POSITIVE LOGITS
     deterrent
    1.03
     headache
    0.96
     contradiction
    0.91
     nuisance
    0.88
     coincidence
    0.87
     barrier
    0.86
     tease
    0.86
     challenge
    0.84
     problem
    0.84
     joke
    0.84
    Activations Density 0.085%

    No Known Activations