© 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. 10-RES-JB
    11. 10711
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or endings of words that are common in various names or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pick
    -0.75
    tr
    -0.69
    mop
    -0.69
    ty
    -0.66
    sed
    -0.66
    picking
    -0.66
     glim
    -0.64
    t
    -0.64
    paren
    -0.64
    mind
    -0.63
    POSITIVE LOGITS
    uthor
    1.33
    ÅŁ
    1.26
    eva
    1.25
    ñ
    1.24
    issance
    1.20
    Äĩ
    1.16
    eus
    1.13
    Äį
    1.12
    ï
    1.10
    ÄŁ
    1.10
    Activations Density 0.198%

    No Known Activations