© 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. 0-RES-JB
    11. 5117
    Prev
    Next
    INDEX
    Explanations

    words related to muscles

    oai_token-act-pair · gpt-3.5-turbo

    words related to music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dumps
    -0.78
     Draper
    -0.69
     relegation
    -0.68
     courier
    -0.67
     drip
    -0.66
     dumping
    -0.66
     dumped
    -0.65
     custody
    -0.65
     Diamond
    -0.65
    LLOW
    -0.65
    POSITIVE LOGITS
    mus
    4.80
    Mus
    2.18
     mus
    1.49
     MUS
    1.42
    mos
    1.38
    imus
    1.34
     Mus
    1.28
    amus
    1.07
    mic
    1.02
    mut
    1.01
    Activations Density 0.003%

    No Known Activations