© 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. 18908
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and services

    oai_token-act-pair · gpt-3.5-turbo

    topics related to technology and its impact on society

    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
    ãĤ¨ãĥ«
    -0.75
    ŃĶ
    -0.71
    ãĤ¢ãĥ«
    -0.62
    ificant
    -0.61
    ãĥ´
    -0.59
    ãģį
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.57
    Ł
    -0.57
    ãĤ©
    -0.54
    PATH
    -0.54
    POSITIVE LOGITS
     or
    0.80
     etc
    0.73
     and
    0.71
    ®,
    0.64
    .
    0.60
     syndrome
    0.60
    ,
    0.59
     versus
    0.59
     rather
    0.58
     ("
    0.57
    Activations Density 0.542%

    No Known Activations