© 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. 6-RES-JB
    11. 21985
    Prev
    Next
    INDEX
    Explanations

    descriptions of complete or full transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    the word "completely" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.88
    rers
    -0.74
    llor
    -0.70
    roe
    -0.69
    elope
    -0.68
    yip
    -0.67
    pring
    -0.67
    mere
    -0.66
    pires
    -0.66
    yer
    -0.65
    POSITIVE LOGITS
     submerged
    0.74
     overhaul
    0.73
     immersed
    0.72
     obliter
    0.72
     revamped
    0.71
     disregard
    0.71
     reliant
    0.70
     renovated
    0.70
     disreg
    0.70
     annihil
    0.69
    Activations Density 0.027%

    No Known Activations