© 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. 7-RES-JB
    11. 16743
    Prev
    Next
    INDEX
    Explanations

    phrases related to fate and historical events

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to fate and history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.68
    insula
    -0.67
    lav
    -0.66
    tein
    -0.66
     UCH
    -0.63
    hirt
    -0.61
     referen
    -0.60
    dL
    -0.60
    ++++
    -0.59
    edin
    -0.58
    POSITIVE LOGITS
    ankind
    1.00
    arily
    0.93
     itself
    0.84
     incarn
    0.77
    utics
    0.76
    's
    0.75
     heals
    0.75
     buffs
    0.74
    icians
    0.72
     Incarn
    0.72
    Activations Density 0.234%

    No Known Activations