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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9788
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration or conflict

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating collaboration and working together within a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andise
    -0.50
    estone
    -0.49
    isec
    -0.49
    xtap
    -0.48
    imity
    -0.48
    produced
    -0.48
    imet
    -0.48
    ãĤ©
    -0.48
    VERTISEMENT
    -0.47
    ication
    -0.47
    POSITIVE LOGITS
     admins
    0.81
     devs
    0.80
     feminists
    0.79
     peasants
    0.79
     subordinates
    0.79
     Palestinians
    0.78
     villagers
    0.78
     anarchists
    0.78
     interns
    0.77
     coworkers
    0.75
    Activations Density 0.812%

    No Known Activations