© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 16344
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical concepts and theories

    oai_token-act-pair · gpt-3.5-turbo

    concepts and language related to probability and statistical theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.87
    ahime
    -0.72
    Cooldown
    -0.71
    Street
    -0.70
    PDATE
    -0.68
    Growing
    -0.68
    gallery
    -0.67
    Club
    -0.67
    GREEN
    -0.66
    FILE
    -0.66
    POSITIVE LOGITS
     presupp
    1.53
     theorem
    1.34
     logically
    1.30
     implies
    1.22
     triv
    1.19
     imply
    1.17
     empir
    1.15
     satisfies
    1.12
     {\
    1.12
     dispro
    1.11
    Activations Density 0.374%

    No Known Activations