© 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 EvalsExportsinterp-engineNEWAPI 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. 3404
    Prev
    Next
    INDEX
    Explanations

    words related to giving or providing opportunities or chances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to flexibility and freedom in various contexts

    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
     Cth
    -0.64
     Warehouse
    -0.62
     corrid
    -0.58
     occurrences
    -0.58
    adish
    -0.58
     extremes
    -0.57
     occurrence
    -0.56
    essel
    -0.55
    jay
    -0.55
     converge
    -0.55
    POSITIVE LOGITS
    thood
    1.01
     opportunity
    0.99
     chance
    0.84
    freedom
    0.78
     boost
    0.78
     cushion
    0.75
    ahead
    0.75
     latitude
    0.75
     opportunities
    0.73
     immunity
    0.72
    Activations Density 0.213%

    No Known Activations