© 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. 7-RES-JB
    11. 21236
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various places or personal names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Ball."

    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
    liness
    -0.71
     Beir
    -0.64
    éĥ
    -0.64
     showc
    -0.63
    ullah
    -0.62
    æĸ¹
    -0.62
    ript
    -0.62
    åİ
    -0.62
     plur
    -0.61
    ä
    -0.60
    POSITIVE LOGITS
    oons
    1.17
    istics
    1.11
    oon
    1.03
    antine
    1.01
    park
    0.98
    asso
    0.96
    asted
    0.91
    ball
    0.90
    istically
    0.89
    haus
    0.89
    Activations Density 0.019%

    No Known Activations