© 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. 17272
    Prev
    Next
    INDEX
    Explanations

    names of individuals, likely authors, designers, and other creators

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names related to creators and contributors in various contexts

    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
    ccording
    -0.82
     resil
    -0.71
    )=
    -0.67
    elfare
    -0.65
     stubborn
    -0.65
     referen
    -0.62
     disarm
    -0.62
    ailable
    -0.59
    ]=
    -0.58
     polarization
    -0.58
    POSITIVE LOGITS
     Jr
    1.09
     Architects
    0.96
     Productions
    0.95
     Associates
    0.90
     (@
    0.88
    kson
    0.86
     Sr
    0.85
     Photography
    0.82
     III
    0.82
     QC
    0.80
    Activations Density 0.285%

    No Known Activations