© 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. 19270
    Prev
    Next
    INDEX
    Explanations

    terms related to the time of taking office or joining a position

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders taking office

    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
    pmwiki
    -0.75
    âĨij
    -0.67
    ļéĨĴ
    -0.66
     contingency
    -0.66
    ãĥĩãĤ£
    -0.63
     variety
    -0.63
    apter
    -0.63
     equivalents
    -0.62
    awatts
    -0.61
    alog
    -0.61
    POSITIVE LOGITS
     landfall
    0.80
     captivity
    0.75
     Trafford
    0.69
     presidency
    0.69
    stad
    0.65
    rament
    0.62
     juven
    0.62
     exile
    0.62
     tenure
    0.61
     Dise
    0.61
    Activations Density 0.305%

    No Known Activations