© 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. 7-RES-JB
    11. 2109
    Prev
    Next
    INDEX
    Explanations

    adjectives related to characteristics or attitudes

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases expressing emotional intensity and outward expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tanz
    -0.70
    PLIED
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    noon
    -0.62
     Bastard
    -0.62
     Credits
    -0.61
    ammy
    -0.60
    Random
    -0.59
    olicy
    -0.58
    Frameworks
    -0.58
    POSITIVE LOGITS
    iations
    0.93
    ously
    0.84
    ous
    0.83
    atively
    0.82
    ologic
    0.78
    ographed
    0.77
    uously
    0.76
    iation
    0.74
    hips
    0.74
    hound
    0.72
    Activations Density 0.097%

    No Known Activations