© 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. 6-RES-JB
    11. 12825
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a contrast or a challenge to a previous statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "though" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pta
    -0.79
    lees
    -0.68
     GEAR
    -0.67
    isible
    -0.67
    enture
    -0.67
    isable
    -0.63
     cryst
    -0.60
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
     nexus
    -0.58
     fundament
    -0.58
    POSITIVE LOGITS
    ts
    1.34
    tons
    1.26
    tern
    0.87
     admittedly
    0.83
    tery
    0.82
    ton
    0.82
    terness
    0.81
    chery
    0.78
    clair
    0.76
    ial
    0.75
    Activations Density 0.029%

    No Known Activations