© 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. 11-RES-JB
    11. 7160
    Prev
    Next
    INDEX
    Explanations

    actions and interactions between people

    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
    amaz
    -0.76
    tained
    -0.70
     Been
    -0.66
    pired
    -0.66
    ceivable
    -0.65
    umbn
    -0.65
    printed
    -0.63
    Þ
    -0.62
     Powered
    -0.62
    pared
    -0.61
    POSITIVE LOGITS
     consequently
    1.10
     reap
    1.07
     vice
    1.05
     manipulate
    1.04
     sometimes
    1.04
     thus
    1.03
     therefore
    1.03
     thereby
    0.98
     communicate
    0.98
     behave
    0.97
    Activations Density 0.309%

    No Known Activations