© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18064
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Isla."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring “ila” in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upt
    -0.77
     quad
    -0.71
     prog
    -0.69
     Quad
    -0.67
     thinkers
    -0.67
    QUIRE
    -0.66
     zero
    -0.66
     wiser
    -0.66
     predictive
    -0.64
    âĺħâĺħ
    -0.63
    POSITIVE LOGITS
    ila
    4.64
    ILA
    2.37
    illa
    1.84
    ilan
    1.45
    ilo
    1.44
    illas
    1.36
    ilia
    1.32
    il
    1.30
    ela
    1.30
    ilar
    1.28
    Activations Density 0.012%

    No Known Activations