© 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. 2-RES-JB
    11. 23925
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroscience or the nervous system

    oai_token-act-pair · gpt-3.5-turbo

    references to neurobiology and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peoples
    -0.73
     Lynch
    -0.71
    ICAN
    -0.70
     Edison
    -0.70
     Burning
    -0.69
     Bundy
    -0.68
     Weaver
    -0.68
     Fif
    -0.68
    UAL
    -0.67
    ablishment
    -0.67
    POSITIVE LOGITS
    sci
    1.08
    scient
    1.08
    genic
    1.06
    phys
    1.04
     neuro
    1.03
    psych
    0.97
     neur
    0.95
    typ
    0.91
    stem
    0.89
    ses
    0.88
    Activations Density 0.004%

    No Known Activations