© 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. 7157
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or condition that needs to be fulfilled before something else can happen

    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
    ãĥĺ
    -0.75
    ãģ®æ
    -0.73
    ardless
    -0.72
    ãģ®éŃĶ
    -0.72
    raq
    -0.70
    rolled
    -0.67
    geist
    -0.67
    eller
    -0.67
    iph
    -0.66
    atform
    -0.64
    POSITIVE LOGITS
     risking
    1.20
     encountering
    1.04
     mentioning
    1.00
     sacrificing
    1.00
     recourse
    0.98
     consulting
    0.94
     knowing
    0.93
     compromising
    0.93
     violating
    0.90
     addressing
    0.89
    Activations Density 0.059%

    No Known Activations