© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17863
    Prev
    Next
    INDEX
    Explanations

    entities or proper nouns, such as names and locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and references to specific entities or organizations

    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
     CrossRef
    -0.77
    ãĢı
    -0.63
     abroad
    -0.63
    )).
    -0.61
     elsewhere
    -0.60
    ãĢį
    -0.60
    ?ãĢį
    -0.59
    .</
    -0.59
     ;)
    -0.59
    ]).
    -0.59
    POSITIVE LOGITS
    ãĥ«
    0.73
    ãĤ¸
    0.65
    ·
    0.64
    ãĥª
    0.62
    ãĤ¤
    0.59
    Winged
    0.58
    omes
    0.58
    rin
    0.57
    ãĥ³
    0.56
    ãĥ¼ãĥ
    0.55
    Activations Density 1.926%

    No Known Activations