© 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. 9932
    Prev
    Next
    INDEX
    Explanations

    phrases referring to methods or approaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe methods or approaches to doing something

    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
    ĸļ
    -0.98
    usters
    -0.75
    orescent
    -0.71
    uster
    -0.71
    oubted
    -0.70
    itor
    -0.65
    noxious
    -0.65
    ropolitan
    -0.65
    elaide
    -0.64
    eele
    -0.63
    POSITIVE LOGITS
    fare
    1.27
    finding
    1.11
    ward
    1.01
    point
    1.00
    forward
    0.97
     forward
    0.94
    points
    0.92
    station
    0.90
    finder
    0.86
    kell
    0.85
    Activations Density 0.049%

    No Known Activations