© 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. 4-RES-JB
    11. 913
    Prev
    Next
    INDEX
    Explanations

    phrases related to international matters, specifically with words starting with 'Int' or 'int'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Int" or "Intelligence" in various contexts

    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
    jriwal
    -0.83
    hyde
    -0.79
    artifacts
    -0.75
    yards
    -0.75
     Gleaming
    -0.74
    ¶ħ
    -0.74
    mith
    -0.73
    */(
    -0.71
    lling
    -0.70
    OHN
    -0.70
    POSITIVE LOGITS
    ention
    1.32
    ellect
    1.31
    ensity
    1.26
    ensive
    1.18
    uitive
    1.16
    ENTION
    1.15
    estinal
    1.07
    ellig
    1.02
    ended
    1.00
    elligence
    1.00
    Activations Density 0.009%

    No Known Activations