© 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. 0-RES-JB
    11. 18286
    Prev
    Next
    INDEX
    Explanations

    words related to participants in various activities or groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to people engaged in various professions or roles

    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
    channelAvailability
    -0.69
    ĻĤ
    -0.63
     relative
    -0.60
     circumst
    -0.60
    ãĥ¬
    -0.59
    ãĥĺãĥ©
    -0.59
    =-=-=-=-=-=-=-=-
    -0.57
     orphan
    -0.56
    chio
    -0.54
     circumstance
    -0.53
    POSITIVE LOGITS
    ers
    4.07
    ERS
    2.42
    ership
    2.32
    er
    2.10
    ering
    2.03
    ered
    1.82
    ER
    1.75
    erers
    1.72
    ings
    1.50
    ees
    1.49
    Activations Density 0.036%

    No Known Activations