© 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. 1-RES-JB
    11. 3418
    Prev
    Next
    INDEX
    Explanations

    terms related to financial or political support

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or organizations that are financially supported by governments or other significant backers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istics
    -0.86
    ogens
    -0.79
     Protocol
    -0.77
    eway
    -0.74
     Colo
    -0.70
     Harbor
    -0.69
    EMS
    -0.69
     Strait
    -0.68
    cial
    -0.66
     Crew
    -0.64
    POSITIVE LOGITS
    backed
    1.19
    interstitial
    1.10
    ynamic
    0.81
    ragon
    0.79
    lash
    0.79
    ratulations
    0.78
    etheless
    0.77
    yip
    0.75
    quartered
    0.75
    bare
    0.72
    Activations Density 0.004%

    No Known Activations