© 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. 0-RES-JB
    11. 12043
    Prev
    Next
    INDEX
    Explanations

    references to tall structures such as towers

    oai_token-act-pair · gpt-3.5-turbo

    references to towers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vegan
    -0.71
     Volunte
    -0.70
     Nixon
    -0.68
     âĸ
    -0.66
    umm
    -0.65
     analges
    -0.65
     Extras
    -0.64
    ubric
    -0.64
     Issues
    -0.63
    allo
    -0.63
    POSITIVE LOGITS
     tower
    3.83
     towers
    2.91
     Tower
    2.60
    tower
    2.43
     Towers
    1.89
     skysc
    1.36
     turret
    1.31
     castle
    1.29
     turrets
    1.21
     skyline
    1.16
    Activations Density 0.016%

    No Known Activations