© 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. 19169
    Prev
    Next
    INDEX
    Explanations

    information related to transportation and security protocols

    oai_token-act-pair · gpt-3.5-turbo

    statistical and numerical information related to tourism and economic impacts

    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
    "))
    -0.69
    NAS
    -0.54
    ascus
    -0.53
    å¥
    -0.53
    dor
    -0.52
    urchase
    -0.52
    ank
    -0.51
    ãĥ¤
    -0.51
    ãĤ¬
    -0.51
    endor
    -0.51
    POSITIVE LOGITS
     however
    0.70
     meanwhile
    0.69
     ensures
    0.59
     overload
    0.56
     abound
    0.56
     attrition
    0.56
     exped
    0.56
     mechanisms
    0.55
     discretion
    0.54
     assures
    0.53
    Activations Density 2.565%

    No Known Activations