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. 8473
    Prev
    Next
    INDEX
    Explanations

    business entities by detecting their names ending with 'Inc'

    oai_token-act-pair · gpt-3.5-turbo

    references to companies and their corporate structures

    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
    =-=-=-=-=-=-=-=-
    -0.81
    pod
    -0.76
    geries
    -0.74
    Textures
    -0.71
    mast
    -0.69
    hide
    -0.69
    schild
    -0.69
    bian
    -0.68
     Hindi
    -0.66
    pmwiki
    -0.64
    POSITIVE LOGITS
     Ltd
    0.99
     subsidiary
    0.96
     Holdings
    0.91
    orporated
    0.89
     subsidiaries
    0.85
    asonic
    0.78
     Corp
    0.77
    ibaba
    0.77
     headquartered
    0.76
     executive
    0.74
    Activations Density 0.048%

    No Known Activations