© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15661
    Prev
    Next
    INDEX
    Explanations

    country names or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to different nationalities or geographical entities

    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
    eatures
    -0.55
     Yose
    -0.54
     anecd
    -0.53
     pestic
    -0.50
    ãĥ´
    -0.49
     pse
    -0.49
     motivational
    -0.49
    76561
    -0.49
    minist
    -0.48
    Downloadha
    -0.48
    POSITIVE LOGITS
    inia
    0.60
    auga
    0.56
    rats
    0.55
    brids
    0.54
    bach
    0.53
     counterpart
    0.52
    lins
    0.52
    isi
    0.51
     or
    0.51
     ..........
    0.51
    Activations Density 0.872%

    No Known Activations