© 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. 6-RES-JB
    11. 3784
    Prev
    Next
    INDEX
    Explanations

    technical terms or jargon, such as "highway" or "NCAA Division I All-American."

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and associated entities, often in a social or political context

    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
    ammers
    -0.55
    iris
    -0.54
    ensibly
    -0.53
    anwhile
    -0.53
     Thiel
    -0.53
    responsible
    -0.52
    gered
    -0.52
    activated
    -0.52
    liest
    -0.52
     Beir
    -0.52
    POSITIVE LOGITS
    Reviewer
    0.66
    ebted
    0.61
     conco
    0.59
     hairst
    0.59
    DragonMagazine
    0.58
     wardrobe
    0.57
     product
    0.55
    âĦ¢
    0.54
     moments
    0.54
     employee
    0.54
    Activations Density 0.993%

    No Known Activations