© 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. 3-RES-JB
    11. 5170
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sufficient or significant amount of something

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate adequacy and sufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iens
    -0.72
    ados
    -0.70
    itu
    -0.68
     ways
    -0.66
     Lies
    -0.64
     Croatian
    -0.64
    osterone
    -0.64
     Destination
    -0.64
     Cause
    -0.63
    orno
    -0.63
    POSITIVE LOGITS
     exting
    0.86
     tuned
    0.83
     equipped
    0.82
    beit
    0.78
    nerg
    0.78
     weakened
    0.77
     endowed
    0.76
     interacted
    0.75
     differentiated
    0.75
     disag
    0.74
    Activations Density 0.022%

    No Known Activations