© 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. 2-RES-JB
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating size or importance

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "bigger" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shire
    -0.80
    gemony
    -0.76
    endant
    -0.75
    endants
    -0.74
    SR
    -0.72
    SEA
    -0.68
    onso
    -0.67
    YR
    -0.67
    KY
    -0.67
    ibel
    -0.67
    POSITIVE LOGITS
    izont
    0.91
     than
    0.86
     eleph
    0.86
     sized
    0.82
    oted
    0.79
     millenn
    0.79
     carniv
    0.77
     intestine
    0.76
     consequential
    0.76
     proble
    0.75
    Activations Density 0.007%

    No Known Activations