© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18381
    Prev
    Next
    INDEX
    Explanations

    locations within a building, specifically focusing on 'hall' and 'hallways'

    oai_token-act-pair · gpt-3.5-turbo

    references to "halls" and related concepts

    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
     Annotations
    -0.73
    EED
    -0.71
    uyomi
    -0.68
    ossibility
    -0.66
    olitics
    -0.66
     Copy
    -0.65
    vernment
    -0.63
    aminer
    -0.62
    odcast
    -0.61
     flakes
    -0.61
    POSITIVE LOGITS
    ways
    1.52
    owed
    1.28
    way
    1.25
    iday
    1.18
    marks
    1.18
    fare
    1.09
    WAY
    1.07
     hall
    1.06
    ows
    1.04
    ibur
    1.03
    Activations Density 0.015%

    No Known Activations