© 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. 13540
    Prev
    Next
    INDEX
    Explanations

    words related to the atmosphere or climate of a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of different types of environments or settings

    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
    drivers
    -0.75
    arations
    -0.71
    kes
    -0.69
    umbn
    -0.66
     Applications
    -0.66
    agged
    -0.65
    ighters
    -0.65
    sight
    -0.65
    arate
    -0.64
    abs
    -0.64
    POSITIVE LOGITS
     conducive
    1.09
     atmosphere
    1.07
     Atmosp
    0.83
     perv
    0.82
     environment
    0.82
    yip
    0.79
     atmosp
    0.77
     revolving
    0.77
    osta
    0.74
     vibe
    0.72
    Activations Density 0.093%

    No Known Activations