© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2550
    Prev
    Next
    INDEX
    Explanations

    instances where something is "based on" a particular concept or idea

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a foundation or basis for various ideas or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stump
    -0.68
    doors
    -0.68
    nder
    -0.67
    loe
    -0.66
    itches
    -0.64
    catch
    -0.62
     protr
    -0.61
     Ney
    -0.61
    yson
    -0.61
     eternity
    -0.60
    POSITIVE LOGITS
     based
    3.45
    based
    2.30
    Based
    2.28
     Based
    2.25
     headquartered
    1.55
     derived
    1.37
     modeled
    1.26
     rooted
    1.23
     depending
    1.22
     basis
    1.15
    Activations Density 0.040%

    No Known Activations