© 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. 7-RES-JB
    11. 2943
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to government bodies or officials

    oai_token-act-pair · gpt-3.5-turbo

    references to the Assembly in a legislative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¦
    -0.72
    oses
    -0.70
    imaru
    -0.68
    onyms
    -0.68
    omorphic
    -0.66
    zsche
    -0.64
    kus
    -0.63
    PLIED
    -0.62
    asive
    -0.62
    ãĤ¨ãĥ«
    -0.62
    POSITIVE LOGITS
    woman
    1.06
    member
    1.05
     Speaker
    0.95
    Assembly
    0.92
    rats
    0.87
    members
    0.84
    holder
    0.81
     speaker
    0.79
    nect
    0.79
    mate
    0.78
    Activations Density 0.024%

    No Known Activations