© 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. 3-RES-JB
    11. 7121
    Prev
    Next
    INDEX
    Explanations

    a wide range of items or options indicating diversity or multiplicity

    oai_token-act-pair · gpt-3.5-turbo

    the concept of diversity or variety in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rollers
    -0.85
    robe
    -0.76
    oug
    -0.74
    ossier
    -0.73
    arching
    -0.71
    jin
    -0.70
    orney
    -0.68
    abad
    -0.68
    orses
    -0.67
    laws
    -0.67
    POSITIVE LOGITS
    ensical
    0.87
     variety
    0.82
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.81
     thereof
    0.76
    ĸļ
    0.73
     Variety
    0.72
     Flavoring
    0.71
    icult
    0.68
     Clever
    0.68
     assortment
    0.67
    Activations Density 0.016%

    No Known Activations