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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 5035
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or representation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating representation or advocacy on behalf of others

    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
    igmatic
    -0.72
    NetMessage
    -0.63
    floor
    -0.63
    igue
    -0.62
    quartered
    -0.62
    Definition
    -0.62
    esters
    -0.60
    oiler
    -0.59
     crept
    -0.59
    acid
    -0.58
    POSITIVE LOGITS
     behalf
    0.97
     Whole
    0.76
     ours
    0.69
     JUSTICE
    0.67
     Yourself
    0.67
     Nations
    0.67
    umbn
    0.65
    xon
    0.63
    enance
    0.63
    ffic
    0.62
    Activations Density 0.078%

    No Known Activations