© 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. 9-RES-JB
    11. 8630
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and physical objects

    oai_token-act-pair · gpt-3.5-turbo

    sentences with significant punctuation or pauses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.72
    izen
    -0.59
    »Ĵ
    -0.57
    ¥
    -0.53
    irie
    -0.51
    vered
    -0.51
    inately
    -0.51
    è£ħ
    -0.51
    ħĭ
    -0.51
    eem
    -0.49
    POSITIVE LOGITS
     whereas
    1.12
     although
    1.11
     but
    1.06
     which
    0.95
     though
    0.93
     namely
    0.93
     however
    0.90
     albeit
    0.88
    but
    0.87
    although
    0.84
    Activations Density 0.580%

    No Known Activations