Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 12240
    Prev
    Next
    INDEX
    Explanations

    phrases that involve emphasizing a particular topic or content

    oai_token-act-pair · gpt-3.5-turbo

    references to time or scheduling elements

    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
    ittal
    -0.77
    quartered
    -0.67
    ichick
    -0.66
    agara
    -0.63
    agues
    -0.62
    orn
    -0.61
    asty
    -0.61
    aird
    -0.61
    etsk
    -0.60
    ery
    -0.60
    POSITIVE LOGITS
     EDITION
    1.21
     STORY
    1.08
     REPORT
    1.06
    AGES
    1.04
     CONTIN
    1.03
    CLASS
    1.00
     AMER
    1.00
     STUD
    1.00
     ORDER
    1.00
    OUT
    1.00
    Activations Density 0.278%

    No Known Activations