© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12717
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically places and people related to the region of Kandahar

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly locations and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bish
    -0.80
    itably
    -0.76
    ãĥ£
    -0.71
    zees
    -0.68
     trooper
    -0.68
    founded
    -0.66
     bapt
    -0.64
    cler
    -0.64
    PDATE
    -0.63
     baptized
    -0.62
    POSITIVE LOGITS
    ahar
    0.87
    ĸļ
    0.82
    atche
    0.82
     Gins
    0.79
    isp
    0.78
    enburg
    0.76
    wich
    0.76
     Kand
    0.75
    iard
    0.75
    arella
    0.75
    Activations Density 0.030%

    No Known Activations