Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14650
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific architectural feature related to legislative or scientific spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of chambers in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ces
    -0.68
    uras
    -0.64
     sporadic
    -0.63
     erratic
    -0.62
     Kindle
    -0.60
    ordan
    -0.59
     Fields
    -0.58
    ku
    -0.57
     scarce
    -0.57
     RBI
    -0.56
    POSITIVE LOGITS
     chamber
    1.47
     chambers
    1.26
    lain
    1.22
     Chamber
    1.01
    door
    0.97
    maid
    0.96
    room
    0.93
    house
    0.86
     Chambers
    0.85
    rooms
    0.85
    Activations Density 0.007%

    No Known Activations