© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    6. 17979
    Prev
    Next
    INDEX
    Explanations

    words related to nominations and nominees

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nominations and nominees for awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plane
    -0.72
     Galile
    -0.71
    plan
    -0.67
    Jewish
    -0.66
     Anon
    -0.63
     Operation
    -0.63
    pat
    -0.62
    MD
    -0.62
    te
    -0.62
    DH
    -0.62
    POSITIVE LOGITS
     nominations
    1.41
     nominees
    1.38
     submissions
    1.13
     nominate
    1.10
     nominating
    1.08
    ettings
    1.05
    daq
    0.99
     nominated
    0.98
    ittees
    0.94
    uggest
    0.89
    Activations Density 0.005%

    No Known Activations