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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 16052
    Prev
    Next
    INDEX
    Explanations

    details related to police actions and criminal investigations

    oai_token-act-pair · gpt-3.5-turbo

    information related to arrests and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     helic
    -0.65
    leigh
    -0.63
     contrace
    -0.61
     gorge
    -0.60
     indo
    -0.59
    amer
    -0.58
     Travels
    -0.58
     CHO
    -0.55
     millenn
    -0.55
     Gorge
    -0.55
    POSITIVE LOGITS
     nor
    1.30
     whatsoever
    1.25
    nor
    1.12
    yet
    1.01
     yet
    0.93
     anymore
    0.86
     till
    0.82
     except
    0.82
     until
    0.81
     anywhere
    0.80
    Activations Density 0.180%

    No Known Activations