© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 3826
    Prev
    Next
    INDEX
    Explanations

    companies or entities related to telecommunication and media industry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of major telecommunications and media companies

    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
    geries
    -0.78
    gery
    -0.73
    ebin
    -0.72
    orically
    -0.71
    lf
    -0.71
    guards
    -0.66
    debian
    -0.66
    oppable
    -0.64
     poet
    -0.63
     painter
    -0.62
    POSITIVE LOGITS
     Corp
    0.80
     Cable
    0.79
     Corporation
    0.77
    NET
    0.69
    nect
    0.69
    Spect
    0.69
    apeake
    0.68
    plex
    0.67
     Stores
    0.67
    conn
    0.64
    Activations Density 0.011%

    No Known Activations