Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20669
    Prev
    Next
    INDEX
    Explanations

    terms related to negotiations and agreements, particularly within the context of collective bargaining

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with collective bargaining and negotiation power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocrates
    -0.89
    anamo
    -0.87
    ican
    -0.81
    ocaly
    -0.80
    arios
    -0.79
    icans
    -0.79
    ograp
    -0.78
    opoulos
    -0.77
    bish
    -0.76
    onso
    -0.76
    POSITIVE LOGITS
     bargaining
    1.20
     union
    0.80
     tong
    0.80
    eering
    0.79
    eer
    0.79
     Barg
    0.78
     unions
    0.78
     agreements
    0.77
     grievance
    0.77
     negotiation
    0.76
    Activations Density 0.019%

    No Known Activations