© 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. 2-RES-JB
    11. 9391
    Prev
    Next
    INDEX
    Explanations

    words related to seniority or hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "senior" in relation to various roles or positions

    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
    Ĥİ
    -0.78
    doors
    -0.76
    pel
    -0.75
    AUT
    -0.67
    apesh
    -0.66
    agen
    -0.64
    ktop
    -0.63
    orious
    -0.63
     Hispan
    -0.62
    plex
    -0.61
    POSITIVE LOGITS
     citiz
    0.98
    iors
    0.89
    ity
    0.81
     counselor
    0.79
    IOR
    0.79
    iate
    0.77
    iating
    0.76
     lecturer
    0.74
     aide
    0.74
     advisor
    0.73
    Activations Density 0.016%

    No Known Activations