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. 7-RES-JB
    6. 5604
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or descriptions referring to a person's period or duration of activity in a particular place or role

    oai_token-act-pair · gpt-3.5-turbo

    references to a period of time or duration related to different contexts

    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
    reme
    -0.74
    ateg
    -0.72
    gru
    -0.68
    cussion
    -0.66
    ellar
    -0.65
    ebted
    -0.65
     yourselves
    -0.64
    urtle
    -0.63
    atem
    -0.63
    anguage
    -0.63
    POSITIVE LOGITS
     abroad
    0.89
     overseas
    0.84
     outdoors
    0.81
     captivity
    0.79
    boarding
    0.75
     captive
    0.72
     tenure
    0.69
    pan
    0.68
    é¾įåĸļ士
    0.68
     stint
    0.68
    Activations Density 0.165%

    No Known Activations