© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 13409
    Prev
    Next
    INDEX
    Explanations

    words related to sensory experiences and emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    elements related to sound production and atmospheric quality in music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olicy
    -0.89
     ineligible
    -0.74
     quotas
    -0.73
     taxpayer
    -0.73
     taxpayers
    -0.71
     subcontract
    -0.70
     eligibility
    -0.70
     Forbes
    -0.70
    Conservative
    -0.69
    eligible
    -0.69
    POSITIVE LOGITS
     sensations
    1.37
     euph
    1.28
     vibrations
    1.22
     throb
    1.22
     sensation
    1.21
     exhilar
    1.21
     trance
    1.18
     puls
    1.18
     ecstasy
    1.16
     palpable
    1.15
    Activations Density 0.774%

    No Known Activations