© 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. 2-RES-JB
    11. 17519
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting speculation or assumption

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assumptions or conjectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zanne
    -0.77
    enko
    -0.72
    uese
    -0.71
    ching
    -0.71
    bara
    -0.70
    abies
    -0.70
    ger
    -0.70
    ament
    -0.70
    arium
    -0.68
    bern
    -0.68
    POSITIVE LOGITS
     unsurprisingly
    0.74
    ãĥ¼ãĥĨãĤ£
    0.72
    æ³
    0.71
     incent
    0.71
    Ń·
    0.70
    ãģ®å®
    0.67
     reside
    0.66
     accommod
    0.65
     ¯
    0.65
     inher
    0.64
    Activations Density 0.007%

    No Known Activations