© 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. 916
    Prev
    Next
    INDEX
    Explanations

    terms related to academic departments or fields of study within higher education institutions, particularly those labeled "Sciences"

    oai_token-act-pair · gpt-4-turbo

    references to different departments or fields within an academic institution

    oai_token-act-pair · gpt-3.5-turbo

    references to academic disciplines related to sciences

    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
    own
    -0.66
    usher
    -0.65
    irth
    -0.63
    shr
    -0.63
    early
    -0.63
    birth
    -0.61
    laun
    -0.60
     Fas
    -0.60
    rel
    -0.59
     Islanders
    -0.58
    POSITIVE LOGITS
     Sciences
    1.22
     sciences
    0.88
     Laboratories
    0.82
    terday
    0.81
    ource
    0.79
     Instruments
    0.78
     Instrument
    0.78
     Advisor
    0.77
    kies
    0.76
     Advis
    0.76
    Activations Density 0.009%

    No Known Activations