© 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. 6-RES-JB
    11. 14439
    Prev
    Next
    INDEX
    Explanations

    keywords related to laws, regulations, and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulations and governmental actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.74
    itably
    -0.73
     flatt
    -0.71
    uckles
    -0.67
    terday
    -0.66
    undy
    -0.66
     yog
    -0.66
     eyebrows
    -0.66
     wool
    -0.65
     chains
    -0.64
    POSITIVE LOGITS
     Advisory
    1.05
     Assessment
    0.97
     Information
    0.97
     Operating
    0.96
     Recogn
    0.94
     Identification
    0.94
     Programme
    0.94
     Package
    0.93
     Files
    0.91
     Account
    0.90
    Activations Density 0.340%

    No Known Activations