© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6522
    Prev
    Next
    INDEX
    Explanations

    adjectives describing feelings or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of skepticism and evaluation about situations or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *.
    -0.74
     POLITICO
    -0.74
    "—
    -0.68
    .</
    -0.66
    .—
    -0.65
    ··
    -0.65
    —
    -0.64
    —"
    -0.64
     ÂŃ
    -0.64
    .?
    -0.62
    POSITIVE LOGITS
     however
    1.18
     alot
    0.77
     though
    0.70
     therefore
    0.67
     tho
    0.65
     stating
    0.59
     utilizing
    0.58
    iliar
    0.54
     utilizes
    0.54
     didnt
    0.53
    Activations Density 1.473%

    No Known Activations