© 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. 19432
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating reasoning or cause-and-effect relationships

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that explain reasons or justifications

    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
    robe
    -0.65
     tuber
    -0.64
    morph
    -0.64
     Roller
    -0.64
    rop
    -0.63
     rou
    -0.63
     phys
    -0.63
     polymorph
    -0.63
    kil
    -0.62
     MM
    -0.62
    POSITIVE LOGITS
     why
    1.05
    why
    0.97
     WHY
    0.93
    soever
    0.87
    Why
    0.80
    utterstock
    0.73
    iterranean
    0.72
     Why
    0.72
    asons
    0.71
    ctuary
    0.71
    Activations Density 0.024%

    No Known Activations