© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 16523
    Prev
    Next
    INDEX
    Explanations

    pronouns related to group interactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "they" and its variations

    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
    fect
    -0.71
     THEM
    -0.67
     them
    -0.64
     âĺħ
    -0.62
     ones
    -0.62
    rior
    -0.61
     Monster
    -0.61
    fecture
    -0.59
    obia
    -0.57
     Domain
    -0.56
    POSITIVE LOGITS
     selves
    0.92
    atically
    0.78
    're
    0.77
     wills
    0.75
    edin
    0.70
    eds
    0.69
    essor
    0.67
    itri
    0.67
    éĹĺ
    0.67
    selves
    0.66
    Activations Density 0.331%

    No Known Activations