© 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. 3-RES-JB
    11. 3190
    Prev
    Next
    INDEX
    Explanations

    When analyzing phrases in documents, it is looking for instances where research is authored by multiple contributors

    oai_token-act-pair · gpt-3.5-turbo

    references to authors or studies within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FUL
    -0.82
    OWS
    -0.70
    OUNT
    -0.69
    esses
    -0.68
    GBT
    -0.67
    canon
    -0.66
    ardless
    -0.66
    @#&
    -0.66
    places
    -0.64
    BO
    -0.64
    POSITIVE LOGITS
     seq
    1.17
    ween
    0.89
    rics
    0.86
     al
    0.83
     et
    0.81
    ree
    0.77
    andum
    0.76
    iation
    0.75
    rix
    0.74
    abus
    0.73
    Activations Density 0.006%

    No Known Activations