© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11202
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the word "ller"

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ller," indicating a focus on names or terms related to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fet
    -0.65
     undefined
    -0.65
     Mavericks
    -0.64
     footh
    -0.63
    ERAL
    -0.63
     Cind
    -0.62
     Bangl
    -0.60
    IRD
    -0.60
    Raw
    -0.57
    ij士
    -0.56
    POSITIVE LOGITS
    ller
    1.19
    wagen
    1.03
    llers
    0.95
    veyard
    0.90
    anguage
    0.85
    anger
    0.82
    wright
    0.81
    worms
    0.80
    atically
    0.79
    andom
    0.78
    Activations Density 0.006%

    No Known Activations