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. 6-RES-JB
    6. 23929
    Prev
    Next
    INDEX
    Explanations

    negative phrases or connotations related to a specific symbol or phrase

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (=
    -0.64
     <@
    -0.63
    enta
    -0.61
     freaking
    -0.59
     artif
    -0.59
     sidx
    -0.59
     carriage
    -0.58
     kil
    -0.57
    ãĥķãĤ¡
    -0.57
    omorphic
    -0.57
    POSITIVE LOGITS
    requires
    0.88
    dayName
    0.83
    feat
    0.79
    were
    0.78
    eatures
    0.77
    include
    0.74
    than
    0.74
    while
    0.74
    dep
    0.72
    Frames
    0.72
    Activations Density 0.113%

    No Known Activations