© 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. 17314
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer science and software development

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "S" in various contexts

    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
     joking
    -0.73
     hatched
    -0.70
    Reviewer
    -0.67
     trolling
    -0.66
     Jehovah
    -0.66
     Finn
    -0.64
     Witch
    -0.63
     Yel
    -0.62
     christ
    -0.62
     psycho
    -0.62
    POSITIVE LOGITS
    ockets
    1.33
    ourced
    1.29
    orting
    1.28
    orted
    1.26
    ustain
    1.25
    amples
    1.24
    ESSION
    1.23
    igma
    1.22
    atellite
    1.22
    olver
    1.20
    Activations Density 0.058%

    No Known Activations