© 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. 2-RES-JB
    11. 5542
    Prev
    Next
    INDEX
    Explanations

    themes related to destruction or negative actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to destruction or harmful actions

    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
    ETF
    -0.88
    annis
    -0.74
    culation
    -0.73
    liner
    -0.70
    ature
    -0.69
    çīĪ
    -0.69
    matic
    -0.65
     pleading
    -0.65
     Demand
    -0.64
    plom
    -0.63
    POSITIVE LOGITS
     havoc
    0.92
    roying
    0.84
     warheads
    0.76
    ãĥĪ
    0.75
     shields
    0.69
     destroy
    0.68
     destroys
    0.68
    ishers
    0.68
    ishing
    0.67
     spoiled
    0.66
    Activations Density 0.019%

    No Known Activations