© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10597
    Prev
    Next
    INDEX
    Explanations

    the presence of various types of sensory stimuli, such as sounds, lights, and smells

    oai_token-act-pair · gpt-3.5-turbo

    auditory experiences or sound-related descriptions

    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
    enture
    -0.77
     Investments
    -0.77
     Loan
    -0.77
     Pension
    -0.77
     alliances
    -0.76
     rosters
    -0.76
    folio
    -0.75
     dismantled
    -0.75
     reformed
    -0.74
     Founding
    -0.72
    POSITIVE LOGITS
     vibrations
    1.57
     vibration
    1.43
     audible
    1.43
     emitted
    1.34
     auditory
    1.24
     sensations
    1.18
     pulses
    1.12
     electromagnetic
    1.12
     transmitted
    1.11
     vibr
    1.11
    Activations Density 0.795%

    No Known Activations