© 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. 15588
    Prev
    Next
    INDEX
    Explanations

    phrases related to modern technology and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    commas in complex sentences

    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
     dozen
    -0.59
    ©¶æ
    -0.57
    jured
    -0.56
     mum
    -0.55
    atorium
    -0.54
    aq
    -0.53
     Soup
    -0.53
    ãĥīãĥ©
    -0.52
    iple
    -0.52
    usha
    -0.52
    POSITIVE LOGITS
     namely
    1.20
    especially
    1.19
    particularly
    1.15
     thereby
    1.06
     culminating
    1.01
     resulting
    1.00
     particularly
    0.97
     especially
    0.96
     hence
    0.91
     irrespective
    0.91
    Activations Density 0.415%

    No Known Activations