© 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. 8-RES-JB
    11. 10735
    Prev
    Next
    INDEX
    Explanations

    named entities like names of news organizations and people

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or character wrappers that indicate sections or attributions in text

    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
     Aph
    -0.69
     Alic
    -0.66
     Mines
    -0.65
     Cyborg
    -0.65
     Loki
    -0.65
     Philips
    -0.64
     Penny
    -0.64
     Scorp
    -0.64
     Prism
    -0.64
     Hog
    -0.63
    POSITIVE LOGITS
    WASHINGTON
    1.00
    CLOSE
    0.84
    LOS
    0.84
    pmwiki
    0.82
    SHARE
    0.82
    Washington
    0.81
    ente
    0.79
    Politics
    0.78
    jer
    0.77
    SAN
    0.77
    Activations Density 0.180%

    No Known Activations