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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13624
    Prev
    Next
    INDEX
    Explanations

    objects that can be carried or used in a bag

    oai_token-act-pair · gpt-3.5-turbo

    references to bags in various contexts

    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
    issance
    -0.75
     Emin
    -0.73
     Edmund
    -0.72
     spect
    -0.67
     relations
    -0.64
     Galile
    -0.64
     Hots
    -0.61
     spectrum
    -0.60
     Pok
    -0.60
     KP
    -0.60
    POSITIVE LOGITS
    gie
    1.56
    ging
    1.35
    gery
    1.32
    ged
    1.32
    glers
    1.19
    bag
    1.16
    gers
    1.11
    gy
    1.10
    pipe
    1.09
    ger
    1.08
    Activations Density 0.032%

    No Known Activations