© 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. 10-RES-JB
    11. 12904
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and companies

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes or divisions in the text

    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
     racket
    -0.87
     plant
    -0.83
     demol
    -0.83
     plants
    -0.81
     creep
    -0.79
     accus
    -0.79
     defective
    -0.79
     amounts
    -0.78
     accrued
    -0.77
     deposits
    -0.76
    POSITIVE LOGITS
    Flickr
    1.56
    Gall
    1.44
    Getty
    1.43
    Wik
    1.40
    Maria
    1.35
    AFP
    1.35
    Nat
    1.32
    CIA
    1.32
    European
    1.28
    Metro
    1.28
    Activations Density 0.049%

    No Known Activations