© 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. 10-RES-JB
    6. 13818
    Prev
    Next
    INDEX
    Explanations

    names or entities related to "Iber"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "iber" and variations of it within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĵĺ
    -0.69
    ¬¼
    -0.62
    Ħ¢
    -0.61
     reservation
    -0.59
    atche
    -0.58
     ECO
    -0.57
    apor
    -0.57
     reusable
    -0.56
    eree
    -0.55
    Desktop
    -0.55
    POSITIVE LOGITS
    tarian
    1.22
    tarians
    1.12
    ts
    1.11
    tes
    1.10
    t
    1.09
    tz
    0.99
    tted
    0.97
    nia
    0.92
    g
    0.88
    gence
    0.88
    Activations Density 0.078%

    No Known Activations