© 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. 1-RES-JB
    11. 22112
    Prev
    Next
    INDEX
    Explanations

    words related to inconsistency or inconsistency itself

    oai_token-act-pair · gpt-3.5-turbo

    references to inconsistency or unevenness in performance or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.87
    entin
    -0.84
    dain
    -0.82
    bernatorial
    -0.76
    uster
    -0.76
    kamp
    -0.74
    ר
    -0.74
    atorium
    -0.73
    erm
    -0.72
    =-=-=-=-
    -0.71
    POSITIVE LOGITS
     inconsist
    1.14
     inconsistent
    1.12
     inconsistency
    0.89
     erratic
    0.87
     buggy
    0.83
     carbohyd
    0.80
    icably
    0.80
     conflicting
    0.79
     unreliable
    0.76
     incons
    0.75
    Activations Density 0.017%

    No Known Activations