© 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. 5379
    Prev
    Next
    INDEX
    Explanations

    action verbs and words related to confrontation or conflict

    oai_token-act-pair · gpt-3.5-turbo

    terms related to offensive actions and military activities

    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
    OGR
    -0.70
    pedia
    -0.68
    ibur
    -0.66
     fantas
    -0.62
    ICS
    -0.62
     awoken
    -0.61
    uthor
    -0.61
     complicit
    -0.60
     CAT
    -0.60
    Plus
    -0.59
    POSITIVE LOGITS
    offensive
    3.32
    eff
    2.04
    attack
    1.41
    went
    1.38
    expensive
    1.37
    stood
    1.26
    sale
    1.16
    alien
    1.13
     obscurity
    0.98
    attacks
    0.97
    Activations Density 0.029%

    No Known Activations