© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 7902
    Prev
    Next
    INDEX
    Explanations

    words related to being the target or focus of attention or scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "object" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leone
    -0.69
    teenth
    -0.68
    ricia
    -0.68
    NPR
    -0.68
    corn
    -0.67
    elsius
    -0.66
    fer
    -0.63
     nerves
    -0.63
     corrid
    -0.63
    ther
    -0.63
    POSITIVE LOGITS
    ivity
    1.27
    ivist
    1.06
    ively
    1.04
    ivism
    1.04
    imus
    1.00
    ified
    0.97
    ifying
    0.96
    ification
    0.96
    ion
    0.94
    ifies
    0.94
    Activations Density 0.016%

    No Known Activations