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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 2-RES-JB
    6. 43
    Prev
    Next
    INDEX
    Explanations

    terms related to the fields of humanities and sciences

    oai_token-act-pair · gpt-3.5-turbo

    references to academic fields, especially those relating to humanities and sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic fields of study, particularly those ending in 'sciences' and 'humanities'

    oai_token-act-pair · gpt-4-turbo
    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
    closure
    -0.65
     captcha
    -0.63
    Dub
    -0.60
     Smy
    -0.60
    cker
    -0.59
     deserted
    -0.57
     erratic
    -0.56
    Registration
    -0.55
    pse
    -0.55
     restrictive
    -0.54
    POSITIVE LOGITS
     disciplines
    0.88
    chool
    0.86
     sciences
    0.84
    ystem
    0.81
     arts
    0.80
    onday
    0.79
    earch
    0.79
    paces
    0.77
     Arts
    0.76
     faculties
    0.75
    Activations Density 0.029%

    No Known Activations