© 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. 4-RES-JB
    11. 7437
    Prev
    Next
    INDEX
    Explanations

    phrases related to a particular name "Iri"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "IRI"

    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
    egg
    -0.92
    spin
    -0.80
    size
    -0.76
    achusetts
    -0.71
    rex
    -0.70
     Granger
    -0.70
    correct
    -0.69
    ablishment
    -0.68
    meal
    -0.67
     Insect
    -0.66
    POSITIVE LOGITS
    yah
    1.04
    ya
    1.03
    oux
    0.87
    ova
    0.85
    iri
    0.85
    uddy
    0.85
    orno
    0.84
    YA
    0.84
    acs
    0.83
    opsis
    0.83
    Activations Density 0.008%

    No Known Activations