© 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. 6-RES-JB
    11. 13599
    Prev
    Next
    INDEX
    Explanations

    expressions of various emotions or attitudes towards a specific topic or situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or disapproval regarding various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goodwin
    -0.69
     Blooming
    -0.63
     constructed
    -0.62
     Narr
    -0.60
     Glover
    -0.59
     Grain
    -0.59
     sear
    -0.58
     waterfall
    -0.57
     shoe
    -0.56
    agog
    -0.56
    POSITIVE LOGITS
    rompt
    0.81
    bia
    0.76
    idad
    0.76
    llah
    0.74
    ociation
    0.73
    ilty
    0.71
    isexual
    0.71
    Letter
    0.70
     displeasure
    0.70
    oche
    0.69
    Activations Density 0.163%

    No Known Activations