© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13423
    Prev
    Next
    INDEX
    Explanations

    phrases related to a process or action taking place

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "process" 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
     anchor
    -0.63
     Flavoring
    -0.62
    immers
    -0.61
    resent
    -0.61
    isd
    -0.58
    ever
    -0.57
     Torn
    -0.55
     Hots
    -0.55
    irie
    -0.55
    undai
    -0.54
    POSITIVE LOGITS
     process
    0.91
    ional
    0.82
    ions
    0.81
    xxxxxxxx
    0.79
    Ĥİ
    0.79
    ivity
    0.79
    æĦ
    0.76
    ivism
    0.76
    IONS
    0.76
    éŃĶ
    0.72
    Activations Density 0.021%

    No Known Activations