Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5623
    Prev
    Next
    INDEX
    Explanations

    text related to legal actions such as being arraigned or reassigned

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of assignments or reassignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     psycho
    -0.62
     craw
    -0.60
    èĪ
    -0.59
     Rain
    -0.59
     rain
    -0.59
    âĨij
    -0.58
     fetal
    -0.57
     Penguin
    -0.57
     Craw
    -0.57
     âĨij
    -0.55
    POSITIVE LOGITS
    igned
    4.47
    igning
    2.75
    ign
    2.18
    ignment
    2.16
    IGN
    1.67
    erved
    1.25
    ignty
    1.24
    essed
    1.13
    pired
    1.12
    ignant
    1.11
    Activations Density 0.015%

    No Known Activations