Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13521
    Prev
    Next
    INDEX
    Explanations

    keywords related to criminal activities like kidnapping, wiretapping, and hijacking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to kidnapping and hijacking incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contrad
    -0.72
     Vlad
    -0.72
     DRAGON
    -0.71
     hereby
    -0.71
     unres
    -0.69
     abundantly
    -0.69
     bitterly
    -0.65
     Rabbit
    -0.65
     deaf
    -0.64
     Flav
    -0.63
    POSITIVE LOGITS
    appings
    1.50
    apping
    1.36
    aping
    1.36
    appers
    1.26
    aped
    1.26
    apped
    1.24
    iking
    1.19
    aps
    1.19
    assing
    1.16
    ribute
    1.13
    Activations Density 0.063%

    No Known Activations