© 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. 18922
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential threats or dangers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a threat or danger

    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
     conglomer
    -0.68
    ocket
    -0.68
     ILCS
    -0.67
    lex
    -0.65
    Ļ½
    -0.65
     Ago
    -0.64
    oyal
    -0.60
    ove
    -0.59
     tongues
    -0.59
     Lust
    -0.59
    POSITIVE LOGITS
     posed
    1.08
     pose
    1.07
     poses
    1.07
    idon
    1.03
     posing
    1.01
    afety
    0.83
    aldehyde
    0.77
    atoon
    0.75
     Pose
    0.72
     ..........
    0.71
    Activations Density 0.018%

    No Known Activations