© 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. 6877
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "hundred" along with related numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to large numbers, particularly in the hundreds

    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
    icter
    -0.80
    acey
    -0.76
    Nav
    -0.75
    kamp
    -0.75
    Creat
    -0.71
    Serv
    -0.70
    Enc
    -0.70
    hra
    -0.69
    obal
    -0.68
    agic
    -0.67
    POSITIVE LOGITS
     thousand
    1.61
     fifty
    1.29
     eighty
    1.24
     dollars
    1.20
     seventy
    1.19
     sixty
    1.17
    ths
    1.17
     hundred
    1.13
     ninety
    1.07
     forty
    1.04
    Activations Density 0.050%

    No Known Activations