© 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. 6525
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'bass'

    oai_token-act-pair · gpt-3.5-turbo

    references to the musical instrument bass and its various contexts

    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
    BY
    -0.74
     AMC
    -0.73
     Cron
    -0.73
     Expend
    -0.72
    ATIONAL
    -0.67
     Bron
    -0.64
     Procedure
    -0.63
     Organizations
    -0.62
     Authority
    -0.61
    OPS
    -0.61
    POSITIVE LOGITS
     bass
    1.34
    nect
    1.24
     guitar
    1.15
     Guitar
    1.09
    bass
    1.06
    inet
    1.04
     Bass
    1.03
     guitars
    1.01
     guitarist
    0.97
    emouth
    0.96
    Activations Density 0.010%

    No Known Activations