© 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. 6-RES-JB
    11. 2757
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a strong personal opinion or belief

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing constancy or long-standing qualities about subjects

    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
    aspx
    -0.79
     VIDEOS
    -0.75
    LESS
    -0.75
    heimer
    -0.73
    externalActionCode
    -0.71
    Loading
    -0.71
    toc
    -0.70
     Bei
    -0.67
    SG
    -0.66
    åĤ
    -0.66
    POSITIVE LOGITS
     fascinated
    0.97
     dreamed
    0.94
     existed
    0.91
     puzzled
    0.84
     regarded
    0.81
    ãĤ«
    0.80
     been
    0.79
    theless
    0.79
     wondered
    0.79
     assumed
    0.78
    Activations Density 0.032%

    No Known Activations