© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 24302
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and personal situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal and legal conflicts or considerations in sensitive situations

    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
     subset
    -0.72
     deviations
    -0.71
     originate
    -0.70
     delegated
    -0.69
     signaled
    -0.69
     utilized
    -0.68
     TAMADRA
    -0.68
     Commerce
    -0.68
     Preferred
    -0.66
     fram
    -0.66
    POSITIVE LOGITS
     counselling
    1.32
     inquest
    1.20
     grieving
    1.10
     rehabilitation
    1.07
     extradition
    1.05
     coroner
    1.01
    Doctors
    1.01
     suing
    1.00
     sympathy
    0.99
    rieve
    0.98
    Activations Density 1.005%

    No Known Activations