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. 10-RES-JB
    6. 20836
    Prev
    Next
    INDEX
    Explanations

    expressions related to ability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capability or potential

    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
    ELD
    -0.71
    bent
    -0.67
    soDeliveryDate
    -0.65
    Appearances
    -0.64
    Qaeda
    -0.61
     Integrity
    -0.61
    quartered
    -0.60
    backer
    -0.60
    hat
    -0.60
    been
    -0.60
    POSITIVE LOGITS
     afford
    1.30
     withstand
    1.24
     muster
    1.21
     cope
    1.14
     achieve
    1.05
     accomplish
    1.05
     communicate
    1.05
     convince
    1.04
     ascertain
    1.04
     discern
    1.03
    Activations Density 0.087%

    No Known Activations