© 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. 7093
    Prev
    Next
    INDEX
    Explanations

    sentences related to software or game updates

    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
     bonded
    -0.87
     imperson
    -0.86
     insensitive
    -0.83
     sensitive
    -0.81
     reluctance
    -0.80
     tiss
    -0.80
     inept
    -0.78
     dismissive
    -0.76
     induction
    -0.74
     therapist
    -0.74
    POSITIVE LOGITS
    Players
    1.52
    Gameplay
    1.37
     Players
    1.37
    Features
    1.21
     Additionally
    1.20
    Along
    1.15
    Xbox
    1.13
    Continue
    1.13
    Additionally
    1.13
     Previously
    1.12
    Activations Density 0.337%

    No Known Activations