© 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. 11-RES-JB
    11. 22092
    Prev
    Next
    INDEX
    Explanations

    references to physical or metaphorical attacks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of attacks or aggressive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.75
    zl
    -0.72
    arden
    -0.66
    ILLE
    -0.61
    ãĤ©
    -0.59
    åħī
    -0.58
    alde
    -0.58
    mberg
    -0.58
    inders
    -0.57
    teness
    -0.57
    POSITIVE LOGITS
     against
    0.96
     vector
    0.96
     waged
    0.89
     vectors
    0.86
    iveness
    0.85
    ivation
    0.84
    ivated
    0.81
    intosh
    0.79
    ive
    0.79
     perpetrated
    0.78
    Activations Density 0.077%

    No Known Activations