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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 8710
    Prev
    Next
    INDEX
    Explanations

    descriptions of assembly instructions or steps

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ranking
    -0.74
    itles
    -0.73
    href
    -0.72
    Synopsis
    -0.71
     esports
    -0.71
     intoxication
    -0.71
     Persona
    -0.69
    Publisher
    -0.68
    arious
    -0.68
     Cognitive
    -0.68
    POSITIVE LOGITS
     screws
    1.40
     glue
    1.32
     drilled
    1.26
     solder
    1.24
     adhesive
    1.21
     scissors
    1.20
     PVC
    1.19
     weld
    1.18
     silicone
    1.17
     seam
    1.16
    Activations Density 0.509%

    No Known Activations