© 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. 6222
    Prev
    Next
    INDEX
    Explanations

    companies, organizations, or entities containing the word "Cor"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific coroner or related entities

    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
    lihood
    -0.93
    éĹĺ
    -0.88
    WAYS
    -0.85
    HAHAHAHA
    -0.85
    WARE
    -0.79
    anwhile
    -0.79
    CRIP
    -0.79
    HAHA
    -0.75
    CLASSIFIED
    -0.73
    xual
    -0.71
    POSITIVE LOGITS
    ruption
    1.32
    porate
    1.23
    rupt
    1.13
    byn
    1.10
    rupted
    1.06
    poral
    1.04
    ridor
    1.04
    por
    1.01
    fman
    1.00
    relation
    0.98
    Activations Density 0.010%

    No Known Activations