© 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. 8-RES-JB
    11. 7881
    Prev
    Next
    INDEX
    Explanations

    indenifying when individuals or entities are joining or coming together with a group or cause

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "join" and its variations, indicating collaboration or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mercial
    -0.76
    intendent
    -0.75
     equival
    -0.70
    framework
    -0.66
    nv
    -0.64
    dayName
    -0.62
    astrous
    -0.60
    oses
    -0.60
    bane
    -0.60
    efficiency
    -0.59
    POSITIVE LOGITS
     forces
    1.08
     ranks
    0.81
     Forces
    0.81
     together
    0.81
     dots
    0.78
     hands
    0.68
    Others
    0.68
    ATURES
    0.66
     classmates
    0.66
     us
    0.65
    Activations Density 0.036%

    No Known Activations