© 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. 3-RES-JB
    11. 15213
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons in terms of quality, superiority, likelihood, or condition

    oai_token-act-pair · gpt-3.5-turbo

    the word "since" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fight
    -0.70
    amina
    -0.68
    ereo
    -0.65
    abus
    -0.65
    hack
    -0.65
    ables
    -0.65
     blows
    -0.62
    Ruby
    -0.62
    iddler
    -0.60
    Rah
    -0.60
    POSITIVE LOGITS
    rely
    1.22
    ĸļ
    0.89
    userc
    0.66
     installing
    0.66
    pite
    0.66
    ciating
    0.65
    since
    0.64
     1961
    0.64
    */(
    0.64
     1945
    0.64
    Activations Density 0.048%

    No Known Activations