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. 10-RES-JB
    6. 1906
    Prev
    Next
    INDEX
    Explanations

    phrases related to casual interactions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to casualness in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.84
    ramid
    -0.74
    ãĥĹ
    -0.73
    amaz
    -0.72
    umbnail
    -0.71
    vez
    -0.71
    burgh
    -0.71
    anic
    -0.71
    rax
    -0.71
    umbing
    -0.69
    POSITIVE LOGITS
     acquaintances
    1.11
     acquaintance
    1.02
     banter
    0.98
     greeting
    0.92
     stroll
    0.92
     chatter
    0.88
     greet
    0.83
     glances
    0.81
     conversation
    0.81
     gossip
    0.81
    Activations Density 0.136%

    No Known Activations