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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 14564
    Prev
    Next
    INDEX
    Explanations

    references to the professional networking platform LinkedIn

    oai_token-act-pair · gpt-3.5-turbo

    mentions of LinkedIn and its related features or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    66666666
    -0.75
    NEY
    -0.70
    phas
    -0.69
    ãĥĺ
    -0.66
    wit
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    050
    -0.64
    090
    -0.63
    ãĥ´
    -0.63
    @#&
    -0.63
    POSITIVE LOGITS
     LinkedIn
    0.99
    LinkedIn
    0.92
     resumes
    0.80
     Connect
    0.79
     Associates
    0.76
    Connection
    0.76
     resume
    0.74
     Hath
    0.73
    ®
    0.73
     networking
    0.71
    Activations Density 0.019%

    No Known Activations