© 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. 18362
    Prev
    Next
    INDEX
    Explanations

    mentions of physical locations or areas, particularly related to public or community spaces

    oai_token-act-pair · gpt-3.5-turbo

    mentions of physical ground locations or properties associated with them

    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
    apt
    -0.76
     Sins
    -0.70
     Abyssal
    -0.68
     Lomb
    -0.66
    thal
    -0.65
    eros
    -0.64
     dime
    -0.64
     gust
    -0.62
    ilde
    -0.62
    arin
    -0.59
    POSITIVE LOGITS
    keepers
    1.12
     grounds
    1.11
    keeper
    1.08
    grounds
    0.93
    ground
    0.93
    keeping
    0.86
    GROUND
    0.86
     Grounds
    0.81
    ãĤ³
    0.78
    bridge
    0.76
    Activations Density 0.015%

    No Known Activations