© 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. 1-RES-JB
    11. 22354
    Prev
    Next
    INDEX
    Explanations

    the word "rob" or variations of "rob"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rob" and its variations related to theft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FK
    -0.77
    Found
    -0.76
    LI
    -0.73
    Condition
    -0.73
    SEE
    -0.73
    Sem
    -0.69
    STD
    -0.67
    Inst
    -0.66
    IK
    -0.65
    Tang
    -0.65
    POSITIVE LOGITS
     rob
    1.45
     robbing
    0.96
     robberies
    0.92
    oise
    0.91
    ometry
    0.89
     robbery
    0.87
    inson
    0.86
    bies
    0.85
    onet
    0.83
    ingly
    0.83
    Activations Density 0.009%

    No Known Activations