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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 2986
    Prev
    Next
    INDEX
    Explanations

    preposition-noun pairs representing locations or actions

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to visual imagery or scenery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accountability
    -0.69
     Disclosure
    -0.68
     Opinion
    -0.60
    Policy
    -0.60
    Asset
    -0.59
     Markets
    -0.58
     Insider
    -0.57
    Media
    -0.57
     DACA
    -0.57
     demographics
    -0.56
    POSITIVE LOGITS
     tubes
    0.72
     protr
    0.70
     bushes
    0.69
     stairs
    0.67
     blades
    0.67
     airst
    0.67
     trunk
    0.65
     tube
    0.65
     unsuspecting
    0.64
     broom
    0.63
    Activations Density 3.114%

    No Known Activations