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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 22454
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating possession or reference

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that refer to individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Course
    -0.66
     srfAttach
    -0.66
    ories
    -0.66
     Sloan
    -0.65
     Goldstein
    -0.61
     Coalition
    -0.61
     Beckham
    -0.61
     dawn
    -0.61
    gee
    -0.61
    cemic
    -0.61
    POSITIVE LOGITS
     hooked
    0.83
    atic
    0.76
     reconsider
    0.75
     deported
    0.74
     laugh
    0.71
     addicted
    0.69
     fooled
    0.69
     pegged
    0.68
     hanged
    0.68
     extrad
    0.68
    Activations Density 0.109%

    No Known Activations