© 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. 7-RES-JB
    6. 13648
    Prev
    Next
    INDEX
    Explanations

    phrases that present contrasting viewpoints or aspects

    oai_token-act-pair · gpt-3.5-turbo

    iterative phrases that signal additional information or elaboration

    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
    Wr
    -0.76
    iddle
    -0.71
    nce
    -0.71
    aston
    -0.70
    atre
    -0.69
    IT
    -0.68
    ATH
    -0.67
    ater
    -0.67
    agus
    -0.66
    anon
    -0.65
    POSITIVE LOGITS
     incorporates
    0.78
     insofar
    0.77
     includes
    0.74
     encourages
    0.74
     acted
    0.74
     cautioned
    0.73
     proceeded
    0.72
     optionally
    0.72
     occasionally
    0.72
     hinted
    0.72
    Activations Density 0.043%

    No Known Activations