© 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. 6-RES-JB
    11. 17574
    Prev
    Next
    INDEX
    Explanations

    locations or settings within various types of facilities

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with specific locations and positions

    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
    psc
    -0.53
    cedented
    -0.52
    İ
    -0.51
    axter
    -0.51
    okin
    -0.51
    worldly
    -0.49
    ornings
    -0.49
    CAST
    -0.48
    yrics
    -0.47
     Pradesh
    -0.47
    POSITIVE LOGITS
    liest
    0.70
     aisle
    0.69
     continuum
    0.67
    iest
    0.66
     portion
    0.66
    osphere
    0.65
     brigade
    0.65
    eers
    0.64
     throne
    0.61
     debacle
    0.60
    Activations Density 0.810%

    No Known Activations