© 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. 9-RES-JB
    11. 3802
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or organizations

    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
    ItemTracker
    -0.80
     Debor
    -0.67
    æĸ¹
    -0.60
     indisp
    -0.57
     vigorous
    -0.57
     AFL
    -0.56
     Avalon
    -0.55
     hippocamp
    -0.55
    printf
    -0.55
    SourceFile
    -0.53
    POSITIVE LOGITS
    izabeth
    1.19
    baum
    1.14
    ength
    1.12
    phia
    1.11
    oad
    1.08
    ijk
    1.07
    estial
    1.05
    ibrary
    1.04
    uxe
    1.04
    ixir
    0.99
    Activations Density 0.064%

    No Known Activations