© 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. 13373
    Prev
    Next
    INDEX
    Explanations

    updates or announcements in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of updates or revisions in information

    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
    aden
    -0.90
    athered
    -0.83
    vasive
    -0.77
    ffiti
    -0.75
    pped
    -0.74
    atra
    -0.72
    uman
    -0.72
    ertility
    -0.71
    enic
    -0.70
    gravity
    -0.70
    POSITIVE LOGITS
     Update
    0.98
     UPDATE
    0.93
    UPDATE
    0.92
    Update
    0.87
     EDIT
    0.86
    :]
    0.84
     Correction
    0.79
    :
    0.77
     Timeline
    0.74
     timeline
    0.74
    Activations Density 0.023%

    No Known Activations