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

    Neuronpedia

    APICircuit 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. 20380
    Prev
    Next
    INDEX
    Explanations

    phrases related to speed or the manner in which something is done

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" and its various occurrences

    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
    apt
    -0.73
    åij
    -0.69
    tty
    -0.68
    acerb
    -0.65
    flags
    -0.65
    uggage
    -0.61
    topic
    -0.60
    é¾
    -0.59
    pty
    -0.59
    raft
    -0.59
    POSITIVE LOGITS
    soever
    1.03
     they
    0.82
    xual
    0.78
     we
    0.71
     humans
    0.65
    eve
    0.65
     organisms
    0.63
     individuals
    0.62
     she
    0.60
     THEY
    0.60
    Activations Density 0.046%

    No Known Activations