© 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. 9-RES-JB
    11. 3379
    Prev
    Next
    INDEX
    Explanations

    phrases related to panoramic views

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scl
    -0.72
    SPONSORED
    -0.65
    SPA
    -0.63
    ELS
    -0.59
     Upton
    -0.57
    sr
    -0.57
    eas
    -0.57
    es
    -0.56
    eenth
    -0.56
    etimes
    -0.56
    POSITIVE LOGITS
    ussia
    1.14
    chid
    1.09
    izons
    1.09
    ific
    1.05
    ussian
    1.02
    izont
    1.00
    phans
    0.99
    andom
    0.97
    ikawa
    0.94
    leans
    0.94
    Activations Density 0.062%

    No Known Activations