© 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. 0-RES-JB
    11. 2831
    Prev
    Next
    INDEX
    Explanations

    terms related to metadata

    oai_token-act-pair · gpt-3.5-turbo

    terms related to metadata or analysis concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Express
    -0.94
     Indo
    -0.83
    âĶĢâĶĢ
    -0.73
     âĶ
    -0.72
     Venezuel
    -0.71
     Indigo
    -0.71
     Anime
    -0.69
    ende
    -0.69
     outlet
    -0.67
    iami
    -0.66
    POSITIVE LOGITS
     meta
    2.03
     ner
    1.97
    meta
    1.37
     Rochester
    1.31
     dick
    1.30
     Meta
    1.26
     ax
    1.16
     cock
    1.15
    Meta
    1.01
     Tyson
    0.98
    Activations Density 0.024%

    No Known Activations