© 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. 4-RES-JB
    11. 10207
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ne' or 'ft' or 'ons' with a strong emphasis on the ending 'ne'

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to anatomical, structural, or scientific terms

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

    No Comments

    Negative Logits
     uproar
    -0.51
     Springs
    -0.51
     Pupp
    -0.51
     Tea
    -0.50
     ribbon
    -0.50
     Franks
    -0.50
     bob
    -0.50
     Grayson
    -0.50
     Bullets
    -0.50
     Plymouth
    -0.49
    POSITIVE LOGITS
    etheless
    0.66
    ctions
    0.65
    ighed
    0.64
    oci
    0.62
    »
    0.61
     dilig
    0.60
     confir
    0.60
    udes
    0.60
    este
    0.58
    NetMessage
    0.58
    Activations Density 0.520%

    No Known Activations