© 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. 4-RES-JB
    11. 24108
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    the word "how" in various contexts

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

    No Comments

    Negative Logits
    isher
    -0.71
    ature
    -0.61
     Ferr
    -0.60
     Tanz
    -0.59
    lehem
    -0.58
     Grail
    -0.58
    agonists
    -0.57
     Nova
    -0.57
    quist
    -0.57
     Guer
    -0.57
    POSITIVE LOGITS
    soever
    1.07
    beit
    0.87
    ever
    0.86
    HCR
    0.86
    ls
    0.85
    ells
    0.85
    ling
    0.82
    much
    0.78
     much
    0.78
    lers
    0.77
    Activations Density 0.076%

    No Known Activations