© 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. 18488
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions statements related to age, race, or other details specified for various applications or services

    oai_token-act-pair · gpt-3.5-turbo

    patterns involving conjunctions, particularly "and" and "or."

    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
    onica
    -0.66
     trump
    -0.66
    leck
    -0.62
    lash
    -0.62
    twitch
    -0.61
    mist
    -0.61
    Shut
    -0.61
    Minecraft
    -0.60
     Freak
    -0.59
    dies
    -0.59
    POSITIVE LOGITS
     hence
    1.23
     thereby
    1.21
     consequently
    1.15
     thereafter
    1.05
     therefore
    1.02
     thus
    0.98
     hereafter
    0.96
     thereto
    0.95
     furthermore
    0.94
     subsequently
    0.93
    Activations Density 0.355%

    No Known Activations