© 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. 11-RES-JB
    11. 22323
    Prev
    Next
    INDEX
    Explanations

    statements expressing opinions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    obligations or recommendations regarding actions that should or should not be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    felt
    -0.72
    ridden
    -0.68
     adolesc
    -0.64
    quickShipAvailable
    -0.62
    Dro
    -0.62
    VIDEO
    -0.62
     Corona
    -0.62
     Xuan
    -0.60
     Gong
    -0.58
    married
    -0.58
    POSITIVE LOGITS
     intervene
    1.20
     reimburse
    1.20
     expel
    1.14
     revoke
    1.13
     undertake
    1.12
     retaliate
    1.12
     announce
    1.11
     allocate
    1.11
     adopt
    1.09
     promul
    1.08
    Activations Density 0.266%

    No Known Activations