© 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. 20897
    Prev
    Next
    INDEX
    Explanations

    terms related to legal documents and official declarations

    oai_token-act-pair · gpt-3.5-turbo

    specific locations or geographical features

    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
     Pog
    -0.57
     Petraeus
    -0.48
    Reloaded
    -0.47
     Farage
    -0.46
     Neb
    -0.45
     Miliband
    -0.45
    OIL
    -0.44
     Xuan
    -0.44
     Canaver
    -0.44
     Dominic
    -0.44
    POSITIVE LOGITS
     respectively
    0.87
    anwhile
    0.60
    *.
    0.59
     guiName
    0.58
    }.
    0.56
    collect
    0.53
    NetMessage
    0.52
     therein
    0.49
    adin
    0.49
    ]).
    0.48
    Activations Density 2.673%

    No Known Activations