© 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. 1-RES-JB
    11. 5315
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities, such as "Ranieri," "Akin," and "Wan."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals and their roles in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.70
     GOODMAN
    -0.69
    PsyNetMessage
    -0.65
    HCR
    -0.65
    */(
    -0.65
     pinpoint
    -0.64
    trial
    -0.64
    quickShipAvailable
    -0.63
    anwhile
    -0.62
     Labrador
    -0.61
    POSITIVE LOGITS
    vier
    1.15
    igans
    1.08
    ieri
    0.98
    interstitial
    0.98
    gha
    0.93
     Ran
    0.93
    sei
    0.89
    opa
    0.89
    zan
    0.88
    agher
    0.87
    Activations Density 0.008%

    No Known Activations