© 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. 7141
    Prev
    Next
    INDEX
    Explanations

    verbs related to disappearance or fading

    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
    ortment
    -0.68
    called
    -0.60
    rius
    -0.59
    leading
    -0.58
    >)
    -0.58
    iola
    -0.57
     Tennis
    -0.57
    iverpool
    -0.56
    builder
    -0.55
     plurality
    -0.54
    POSITIVE LOGITS
     into
    1.17
     away
    1.12
     peacefully
    1.02
     altogether
    0.97
     INTO
    0.95
     mysteriously
    0.93
     overnight
    0.88
     completely
    0.88
     entirely
    0.87
     unnoticed
    0.87
    Activations Density 0.115%

    No Known Activations