© 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. 8-RES-JB
    11. 9460
    Prev
    Next
    INDEX
    Explanations

    words related to listening or auditory activities

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "listen to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.91
    hra
    -0.82
    recy
    -0.82
    union
    -0.76
    nir
    -0.76
    rio
    -0.73
    isoft
    -0.71
    oval
    -0.71
    iasis
    -0.71
    hesion
    -0.70
    POSITIVE LOGITS
     podcasts
    1.06
     voices
    0.98
     music
    0.94
     audi
    0.93
     Voices
    0.93
     hear
    0.88
     tapes
    0.88
     noises
    0.81
     recordings
    0.81
     chatter
    0.80
    Activations Density 0.045%

    No Known Activations