© 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. 4-RES-JB
    11. 6313
    Prev
    Next
    INDEX
    Explanations

    phrases related to the word "fuzz" and variants like "fuzzing" or "fuzzed"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fuzz" and its variations

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

    No Comments

    Negative Logits
     Walton
    -0.65
    ©¶æ
    -0.60
     thieves
    -0.60
     blinded
    -0.59
     Athlet
    -0.59
     wills
    -0.58
     dedication
    -0.57
     Defenders
    -0.57
    brance
    -0.56
     repentance
    -0.56
    POSITIVE LOGITS
    uzz
    1.06
    arro
    0.89
    arella
    0.86
    iest
    0.84
    ombies
    0.83
    ileaks
    0.83
    feed
    0.83
    etta
    0.81
    er
    0.81
    atto
    0.81
    Activations Density 0.007%

    No Known Activations