© 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. 17830
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles related to education administration, specifically the term "Superintendent."

    oai_token-act-pair · gpt-3.5-turbo

    references to educational or organizational administrators

    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
    bra
    -0.79
    etimes
    -0.78
    axy
    -0.71
    ankind
    -0.70
    stra
    -0.69
    ero
    -0.67
    tera
    -0.66
    thal
    -0.66
    liber
    -0.66
    jiang
    -0.65
    POSITIVE LOGITS
     Superintendent
    1.20
    intendent
    1.05
     superintendent
    0.97
    ially
    0.87
    IAL
    0.75
    ãĥ¼ãĥĨãĤ£
    0.74
    hesis
    0.73
     Commissioner
    0.70
     Mick
    0.70
    iate
    0.67
    Activations Density 0.010%

    No Known Activations