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. 9-RES-JB
    6. 20340
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication - especially interactions involving talking to others

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals involved in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å§
    -0.69
    Pg
    -0.65
    Wr
    -0.65
     certificates
    -0.56
     citation
    -0.56
     shipments
    -0.55
    fighting
    -0.54
     bets
    -0.54
     Species
    -0.54
     Wins
    -0.53
    POSITIVE LOGITS
     about
    1.10
     regarding
    1.05
     representatives
    0.94
     concerning
    0.89
     backstage
    0.88
    about
    0.87
     ABOUT
    0.81
    è¦ļéĨĴ
    0.80
     representative
    0.79
     beforehand
    0.79
    Activations Density 0.408%

    No Known Activations