© 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. 10-RES-JB
    11. 18611
    Prev
    Next
    INDEX
    Explanations

    sentences indicating negative events or situations

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings that convey impactful or conclusive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ',"
    -0.61
    lled
    -0.59
    Thumbnail
    -0.58
    inguishable
    -0.58
    '."
    -0.54
    ucer
    -0.53
    untarily
    -0.53
     Cup
    -0.52
    Instance
    -0.51
    Mobil
    -0.49
    POSITIVE LOGITS
    ↵Âł
    1.18
     Âł
    1.13
     Âł Âł
    1.09
     ³³
    1.09
    ³³
    1.05
     americ
    0.94
     Secondly
    0.92
    Âł
    0.88
    tumblr
    0.84
    ↵↵
    0.83
    Activations Density 0.493%

    No Known Activations