© 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
    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. 547
    Prev
    Next
    INDEX
    Explanations

    specific tokens related to unidentified entities or categories, such as 'Any'

    oai_token-act-pair · gpt-3.5-turbo

    general terms and references related to unspecified categories or entities

    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
     Zin
    -0.66
    pard
    -0.64
     Kore
    -0.64
     Newman
    -0.64
     Loren
    -0.62
     Swanson
    -0.61
     SX
    -0.60
     Celest
    -0.60
     Buckley
    -0.58
    Reviewer
    -0.58
    POSITIVE LOGITS
    Í
    0.82
    odox
    0.72
     guiActive
    0.69
    aughs
    0.66
    cffff
    0.65
     ]
    0.64
    ription
    0.63
     abbre
    0.63
    wcsstore
    0.62
     physic
    0.62
    Activations Density 0.291%

    No Known Activations