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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 4338
    Prev
    Next
    INDEX
    Explanations

    terms related to morale and cohesion in a group or organization

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with morale and cohesion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.79
     Nether
    -0.77
    ortion
    -0.76
    sighted
    -0.75
    falls
    -0.75
    Desktop
    -0.74
    Applications
    -0.74
    insert
    -0.71
    alone
    -0.68
    Minecraft
    -0.68
    POSITIVE LOGITS
     morale
    1.57
     veter
    1.06
     cohesion
    0.98
     tremend
    0.94
    ilitary
    0.92
     comr
    0.88
     exha
    0.86
     conclud
    0.82
     conflic
    0.80
    phis
    0.79
    Activations Density 0.022%

    No Known Activations