© 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. 8-RES-JB
    11. 6552
    Prev
    Next
    INDEX
    Explanations

    words related to legislation and government actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulations and legal requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bomber
    -0.68
     remem
    -0.68
     Niet
    -0.67
     whirlwind
    -0.67
    luck
    -0.66
     amaz
    -0.65
     proverb
    -0.65
     Bones
    -0.65
     aback
    -0.65
     Desmond
    -0.65
    POSITIVE LOGITS
     complying
    1.02
     subsidiaries
    1.02
     infringing
    0.99
     exempt
    0.99
     unlawfully
    0.96
     lawfully
    0.94
     infring
    0.94
     cybersecurity
    0.91
     federally
    0.91
    license
    0.86
    Activations Density 0.812%

    No Known Activations