© 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. 10-RES-JB
    11. 17500
    Prev
    Next
    INDEX
    Explanations

    references to disciplinary actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    events related to suspensions or disciplinary actions

    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
    eneg
    -0.85
    slave
    -0.80
    ļéĨĴ
    -0.79
    iro
    -0.78
    quished
    -0.77
     Nanto
    -0.77
    ported
    -0.77
    atche
    -0.76
    £ı
    -0.75
    Magikarp
    -0.75
    POSITIVE LOGITS
     Hill
    1.84
    Hill
    1.71
     Hall
    1.67
    Hall
    1.64
     Halls
    1.36
     hall
    1.25
     Bell
    1.22
    hall
    1.22
     hill
    1.18
    Bell
    1.17
    Activations Density 0.320%

    No Known Activations