© 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. 9-RES-JB
    11. 9863
    Prev
    Next
    INDEX
    Explanations

    proper names and locations marked by a distinct symbol 'âĢĶ'

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that appear as formatted or styled headings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opian
    -0.76
     tack
    -0.75
     rele
    -0.72
     foc
    -0.71
     distingu
    -0.70
     distribut
    -0.69
     perspect
    -0.68
     derog
    -0.68
     comprom
    -0.67
     graz
    -0.67
    POSITIVE LOGITS
     Thousands
    1.21
     Dozens
    1.18
     Authorities
    1.14
     Hundreds
    1.10
     Despite
    1.08
     Researchers
    1.05
     Officials
    1.05
     Investigators
    1.04
     Nearly
    1.04
     Former
    1.02
    Activations Density 0.035%

    No Known Activations