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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2-RES-JB
    6. 19620
    Prev
    Next
    INDEX
    Explanations

    mentions of different communities, such as residential communities, religious communities, and ethnic communities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of community across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.76
    glers
    -0.73
    tered
    -0.71
    inen
    -0.70
    iang
    -0.68
    otomy
    -0.67
    cer
    -0.67
    peror
    -0.67
    gyn
    -0.67
    argon
    -0.67
    POSITIVE LOGITS
     councils
    0.84
     elders
    0.74
     council
    0.73
     outreach
    0.72
     community
    0.70
     communities
    0.70
     redes
    0.69
     fathers
    0.67
     Communities
    0.66
     Torah
    0.66
    Activations Density 0.031%

    No Known Activations