© 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. 8-RES-JB
    11. 874
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Fun"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Fun" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.84
     bearer
    -0.65
     Centauri
    -0.64
     ib
    -0.61
     Hector
    -0.60
    ATTLE
    -0.59
    Minimum
    -0.59
     Sinai
    -0.58
     mole
    -0.57
     Sapphire
    -0.57
    POSITIVE LOGITS
    nel
    1.41
    ctions
    1.38
    eral
    1.31
    imation
    1.30
    nels
    1.21
    nell
    1.07
    ctors
    1.01
    ctor
    0.99
    ilial
    0.98
    geoning
    0.96
    Activations Density 0.028%

    No Known Activations