© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    words related to content creation professions, such as creators, builders, designers, musicians, and producers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to creative professionals and their work

    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
     Territories
    -0.81
    OUS
    -0.69
    yss
    -0.67
     Plane
    -0.66
    athan
    -0.65
     Virus
    -0.65
     Hus
    -0.63
    Knight
    -0.63
     Hume
    -0.63
     Operation
    -0.62
    POSITIVE LOGITS
    paces
    1.49
    hip
    1.39
    pace
    1.27
    mith
    1.22
    ervatives
    1.17
    uggest
    1.13
    hips
    1.11
    chool
    1.03
    poons
    1.02
    ervative
    1.02
    Activations Density 0.189%

    No Known Activations