© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10734
    Prev
    Next
    INDEX
    Explanations

    words related to physical health conditions, specifically conditions related to skin and genitalia

    oai_token-act-pair · gpt-3.5-turbo

    references to arts and creative expressions

    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
    ntil
    -0.69
    è¦ļéĨĴ
    -0.65
     occas
    -0.64
     cumbers
    -0.62
     dime
    -0.62
    berman
    -0.59
    EVA
    -0.58
     exha
    -0.58
     srfAttach
    -0.57
     revelation
    -0.57
    POSITIVE LOGITS
    heet
    1.06
    emis
    0.89
    ilda
    0.87
    heid
    0.85
    esian
    0.85
    arts
    0.84
    irtual
    0.80
    manship
    0.79
    ongs
    0.78
    ilver
    0.73
    Activations Density 0.008%

    No Known Activations