© 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. 495
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests or invitations

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts

    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
    typ
    -0.78
     stru
    -0.66
     partitions
    -0.63
     flakes
    -0.62
    pict
    -0.62
     packets
    -0.60
    stuff
    -0.59
     delet
    -0.57
    pie
    -0.57
     wastes
    -0.57
    POSITIVE LOGITS
     ensure
    1.06
     commemorate
    1.05
     celebrate
    1.05
    adies
    1.05
     promote
    1.03
    wered
    0.98
     accommodate
    0.97
     preserve
    0.96
     maximize
    0.95
    ilet
    0.94
    Activations Density 0.412%

    No Known Activations