© 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. 11-RES-JB
    11. 5156
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and discussions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.60
    venth
    -0.57
    sylv
    -0.56
    cule
    -0.53
    prise
    -0.52
    forth
    -0.49
    Override
    -0.48
    ãĥĨãĤ£
    -0.47
    ãĤ©
    -0.47
    igm
    -0.47
    POSITIVE LOGITS
     according
    0.85
     but
    0.81
     huh
    0.79
     although
    0.71
     whereas
    0.70
     albeit
    0.69
     says
    0.69
     prompting
    0.68
     including
    0.66
     however
    0.66
    Activations Density 0.487%

    No Known Activations