© 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. 3948
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities such as robbery, assault, theft, burglary, and prostitution

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

    references to various types of theft and robbery offenses

    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
    Reviewer
    -0.81
    çĦ
    -0.75
    SPA
    -0.74
     Pixie
    -0.73
    mitt
    -0.71
    iquette
    -0.70
    LESS
    -0.69
    rir
    -0.69
    ffen
    -0.69
    Xi
    -0.68
    POSITIVE LOGITS
     robberies
    1.04
    sters
    1.02
     spree
    1.01
    bery
    1.01
     robbery
    1.00
     thefts
    0.91
     attempt
    0.90
     perpetrated
    0.87
     attempts
    0.83
     robbed
    0.83
    Activations Density 0.079%

    No Known Activations