© 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. 10798
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a person named "Ik" or "Ikhs"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "ik."

    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
    FFFF
    -0.75
     Winchester
    -0.71
     halves
    -0.65
    DIT
    -0.65
    LOAD
    -0.62
    PDATE
    -0.60
    mpeg
    -0.60
     poppy
    -0.59
     Merry
    -0.58
     vested
    -0.57
    POSITIVE LOGITS
    achu
    1.26
    ernels
    1.12
    ernel
    1.06
    athon
    1.04
    yu
    1.04
    owski
    1.04
    istan
    1.01
    atsu
    0.98
    hs
    0.96
    ileaks
    0.95
    Activations Density 0.017%

    No Known Activations