Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6781
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Iterator
    -0.71
    upon
    -0.70
    nuts
    -0.70
    ature
    -0.65
    AppData
    -0.64
    well
    -0.61
    ivo
    -0.61
    helm
    -0.61
    OGR
    -0.60
    rays
    -0.60
    POSITIVE LOGITS
     eve
    1.31
     heels
    1.20
     outskirts
    1.16
     grounds
    1.15
     occasion
    1.14
     basis
    1.10
     verge
    1.07
     sidelines
    1.07
     brink
    1.05
     shores
    0.99
    Activations Density 0.148%

    No Known Activations