© 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. 3-RES-JB
    11. 23020
    Prev
    Next
    INDEX
    Explanations

    mentions of the news agency "AFP."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the news agency AFP

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.92
     Sears
    -0.72
    tons
    -0.71
    pron
    -0.66
    sbm
    -0.64
     Argon
    -0.63
     Raspberry
    -0.63
    liest
    -0.63
    thal
    -0.63
    making
    -0.62
    POSITIVE LOGITS
    UTERS
    0.91
    DEF
    0.87
     PHOTO
    0.82
    sburg
    0.81
     confir
    0.79
    TN
    0.75
    aukee
    0.74
    LV
    0.72
    attle
    0.72
    NG
    0.72
    Activations Density 0.006%

    No Known Activations