© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration or partnership

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cooperation or joint 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
    Story
    -0.66
    awed
    -0.65
    abe
    -0.65
    Merit
    -0.64
    room
    -0.63
    abre
    -0.62
    ayers
    -0.61
     Votes
    -0.60
    pin
    -0.60
    esh
    -0.60
    POSITIVE LOGITS
     conjunction
    3.60
     tandem
    1.43
     combination
    1.20
     conj
    1.06
     unison
    1.02
     totality
    1.00
     lieu
    1.00
     relation
    0.96
     partnership
    0.96
     junction
    0.96
    Activations Density 0.020%

    No Known Activations