© 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. 4567
    Prev
    Next
    INDEX
    Explanations

    names or words containing the sequence "iar"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences or references to a specific character or name

    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
    oak
    -0.66
    UX
    -0.65
    CRIP
    -0.62
     Startup
    -0.62
     Vend
    -0.61
     Concord
    -0.61
     Santos
    -0.61
    AX
    -0.60
    hetamine
    -0.59
    anwhile
    -0.58
    POSITIVE LOGITS
    iar
    0.89
    osc
    0.86
    iosity
    0.83
    ité
    0.81
    atus
    0.78
    ror
    0.78
    alia
    0.78
    osaurs
    0.78
    ate
    0.77
    ates
    0.77
    Activations Density 0.016%

    No Known Activations