© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3990
    Prev
    Next
    INDEX
    Explanations

    words related to violent actions and incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to individuals or groups involved in controversial actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    idth
    -0.65
    ennial
    -0.60
    ometime
    -0.59
    orah
    -0.59
    untled
    -0.59
    ouver
    -0.55
    eanor
    -0.55
    使
    -0.54
    colored
    -0.54
    omever
    -0.53
    POSITIVE LOGITS
     UK
    0.75
     Australian
    0.74
     NZ
    0.71
     Australians
    0.71
    ?".
    0.70
     Nato
    0.69
     rubbish
    0.69
     (£
    0.69
     Australia
    0.67
     BBC
    0.67
    Activations Density 1.301%

    No Known Activations