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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 12076
    Prev
    Next
    INDEX
    Explanations

    specific entities like countries, medical conditions, government bodies, physical objects, and other entities in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or significance related to entities, values, or influences

    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
     Played
    -0.67
     rocked
    -0.61
    Mania
    -0.60
    ravel
    -0.60
    esters
    -0.59
    committee
    -0.58
    eah
    -0.58
     Perspective
    -0.56
    ogun
    -0.56
     Dems
    -0.55
    POSITIVE LOGITS
     secrets
    0.75
     ult
    0.74
     requisite
    0.71
    è¦ļéĨĴ
    0.69
     Whats
    0.65
     necessary
    0.65
     obligations
    0.64
     wisdom
    0.64
     pertinent
    0.63
     traumatic
    0.63
    Activations Density 0.576%

    No Known Activations