© 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 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. 2-RES-JB
    11. 14420
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "escape"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or term related to "esc."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monthly
    -0.72
     NRA
    -0.67
     Surface
    -0.66
     Kinect
    -0.65
     Cruiser
    -0.64
    女
    -0.63
     Borderlands
    -0.62
     à¨
    -0.61
     Gamergate
    -0.61
     lifetime
    -0.60
    POSITIVE LOGITS
    aped
    1.28
    ribed
    1.17
    ript
    1.16
    apes
    1.14
    autions
    1.11
    ence
    1.09
    orts
    1.05
    opes
    1.01
    itals
    1.01
    apers
    0.99
    Activations Density 0.008%

    No Known Activations