© 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. 10-RES-JB
    11. 16627
    Prev
    Next
    INDEX
    Explanations

    places or objects being examined or scrutinized

    oai_token-act-pair · gpt-3.5-turbo

    mentions of products, situations, and examinations related to investigative or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hugs
    -0.68
     laughs
    -0.65
    ĺħ
    -0.65
    å§
    -0.63
    udeb
    -0.61
    Interstitial
    -0.61
    ãģ®å®
    -0.59
    POSE
    -0.59
    ¬¼
    -0.58
    Ń·
    -0.58
    POSITIVE LOGITS
     carefully
    1.31
     closely
    1.31
     extensively
    1.22
     thoroughly
    1.22
     objectively
    1.05
     separately
    0.98
     diligently
    0.97
     aloud
    0.91
     periodically
    0.90
     meticulously
    0.89
    Activations Density 0.467%

    No Known Activations