© 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. 3618
    Prev
    Next
    INDEX
    Explanations

    news article citations

    oai_token-act-pair · gpt-3.5-turbo

    references to original publication sources and related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     objects
    -0.62
     hom
    -0.62
    akuya
    -0.60
     cones
    -0.60
     stren
    -0.58
    ighting
    -0.58
    beit
    -0.58
    ct
    -0.57
     presets
    -0.57
     connectors
    -0.57
    POSITIVE LOGITS
     HuffPost
    0.91
     POLITICO
    0.90
     Huffington
    0.88
    ribune
    0.83
     Published
    0.81
     Publication
    0.81
    Issue
    0.80
     VICE
    0.80
     column
    0.78
    guard
    0.78
    Activations Density 0.107%

    No Known Activations