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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 12636
    Prev
    Next
    INDEX
    Explanations

    verbs related to being selected or invited

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix "-ed" and "-ing" in verbs

    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
    ©¶æ
    -0.82
    cknow
    -0.75
    ood
    -0.70
    etheless
    -0.70
    talk
    -0.67
    ·
    -0.66
    padding
    -0.63
    pton
    -0.63
    undo
    -0.63
    tumblr
    -0.62
    POSITIVE LOGITS
    oga
    0.77
    DERR
    0.71
    ucky
    0.71
     Jupiter
    0.70
    iting
    0.70
    irling
    0.70
    IFIED
    0.69
    efe
    0.68
    aukee
    0.67
    FIELD
    0.65
    Activations Density 0.020%

    No Known Activations