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. 5449
    Prev
    Next
    INDEX
    Explanations

    phrases related to the end or conclusion of a text or sentence

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or visual breaks in the text

    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
    »Ĵ
    -0.86
    REF
    -0.82
    ħĭ
    -0.77
    poon
    -0.74
    SW
    -0.67
    opted
    -0.66
    acea
    -0.66
    LOAD
    -0.66
    ¿½
    -0.63
     unemploy
    -0.61
    POSITIVE LOGITS
     sidx
    0.75
     SHARES
    0.74
     Emails
    0.68
     Thumbnails
    0.66
     IMAGES
    0.63
    hran
    0.62
     SPACE
    0.61
     Looks
    0.61
    utters
    0.61
     Entered
    0.61
    Activations Density 0.038%

    No Known Activations