© 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. 9-RES-JB
    11. 20786
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veterinarian
    -0.51
     preferably
    -0.50
     tragically
    -0.50
     notoriously
    -0.49
    Fortunately
    -0.49
     ensu
    -0.48
    Luckily
    -0.48
    arthy
    -0.48
     happiest
    -0.48
     rightfully
    -0.46
    POSITIVE LOGITS
    arthed
    0.66
    MSN
    0.57
    DCS
    0.55
    ebus
    0.55
    romeda
    0.54
    EStream
    0.52
    tions
    0.51
     ----------------------------------------------------------------
    0.51
    results
    0.51
    }.
    0.51
    Activations Density 1.514%

    No Known Activations