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. 21097
    Prev
    Next
    INDEX
    Explanations

    the phrase "for the most part."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating generalizations or common observations

    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
     sleeper
    -0.76
    Dream
    -0.71
    Chair
    -0.65
     plum
    -0.59
     laure
    -0.59
     DRAGON
    -0.59
    antha
    -0.59
    Draft
    -0.58
    Lock
    -0.57
     chair
    -0.55
    POSITIVE LOGITS
    Downloadha
    0.99
    aking
    0.77
    ridges
    0.76
    agements
    0.69
    ials
    0.67
    ilers
    0.65
    uncture
    0.65
    icularly
    0.63
    ridge
    0.63
    ña
    0.62
    Activations Density 0.012%

    No Known Activations