© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "denigrate"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "denigrate" and its variations

    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
     hitch
    -0.69
     coinc
    -0.68
    lease
    -0.63
     Piper
    -0.61
     Cue
    -0.58
     minded
    -0.57
     crunch
    -0.57
     permitting
    -0.56
     Shall
    -0.56
     towed
    -0.55
    POSITIVE LOGITS
    unci
    1.61
    unciation
    1.60
    izens
    1.51
    igrated
    1.51
    ounces
    1.47
    igr
    1.40
    iability
    1.35
    igration
    1.35
    igrate
    1.35
    iable
    1.32
    Activations Density 0.028%

    No Known Activations