© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14719
    Prev
    Next
    INDEX
    Explanations

    words related to skeletons, skepticism, and specific terms containing "Ske"

    oai_token-act-pair · gpt-3.5-turbo

    references to skepticism and critical perspectives

    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
    rontal
    -0.77
    etheless
    -0.76
     guiActiveUnfocused
    -0.74
     FISA
    -0.73
    HCR
    -0.63
    女
    -0.61
     unification
    -0.61
     fluorescent
    -0.60
    riott
    -0.59
     1918
    -0.59
    POSITIVE LOGITS
    letal
    1.10
    leton
    1.06
     Ske
    1.00
    ley
    0.85
    chers
    0.84
    leys
    0.81
    ptic
    0.81
    cano
    0.80
    cius
    0.79
    bridge
    0.79
    Activations Density 0.010%

    No Known Activations