© 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. 9-RES-JB
    11. 11299
    Prev
    Next
    INDEX
    Explanations

    instances of something "falling short" or failing to meet a certain standard

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating shortcomings or deficiencies

    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
    eer
    -0.65
    cape
    -0.61
     Stuff
    -0.57
    jug
    -0.56
     transformation
    -0.53
     confiscated
    -0.52
     retrieved
    -0.52
    sequence
    -0.52
     unfold
    -0.51
     spree
    -0.51
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.97
    acies
    0.83
     squarely
    0.82
    Tier
    0.78
    ãĤ©
    0.74
     furthe
    0.74
     closest
    0.71
    pha
    0.67
    Behind
    0.66
     shy
    0.64
    Activations Density 0.183%

    No Known Activations