© 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. 8348
    Prev
    Next
    INDEX
    Explanations

    reptiles and larger animals such as whales and big cats

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of animals and their behaviors

    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
    ãĤ¡
    -0.85
     Assets
    -0.77
     Policies
    -0.76
     deferred
    -0.75
     Coverage
    -0.75
     ISBN
    -0.69
     principals
    -0.69
     WRITE
    -0.68
     Implementation
    -0.67
     prescriptions
    -0.67
    POSITIVE LOGITS
     hiber
    1.41
     mating
    1.29
     extinct
    1.22
     nests
    1.20
     sightings
    1.19
     prow
    1.19
     nesting
    1.17
     inhab
    1.16
     sighting
    1.14
     perched
    1.13
    Activations Density 0.473%

    No Known Activations