© 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
    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. 3807
    Prev
    Next
    INDEX
    Explanations

    phrases related to differing viewpoints or perspectives

    oai_token-act-pair · gpt-3.5-turbo
    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
    incinn
    -0.79
    ratulations
    -0.74
    sylv
    -0.71
    packed
    -0.67
    foreseen
    -0.64
     constituent
    -0.63
    interrupted
    -0.63
     consecut
    -0.63
     Parenthood
    -0.63
    ciating
    -0.62
    POSITIVE LOGITS
     of
    0.83
     prevailing
    0.80
    isms
    0.75
     asc
    0.73
    lance
    0.71
     notions
    0.68
    ologies
    0.67
     view
    0.66
     thereof
    0.66
     beliefs
    0.65
    Activations Density 0.195%

    No Known Activations