© 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. 28
    Prev
    Next
    INDEX
    Explanations

    phrases related to management and planning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to organizational challenges and inefficiencies

    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
     GOODMAN
    -1.03
    ozo
    -0.79
    wana
    -0.75
    afort
    -0.75
    owers
    -0.74
    ãĤ¨ãĥ«
    -0.73
    illance
    -0.72
    uggle
    -0.70
    meric
    -0.70
    rossover
    -0.69
    POSITIVE LOGITS
     failings
    1.61
     failures
    1.51
     incompetence
    1.50
     woes
    1.44
     shortcomings
    1.43
     blame
    1.43
     deficiencies
    1.38
     faults
    1.37
     inadequ
    1.36
     failure
    1.36
    Activations Density 0.873%

    No Known Activations