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. 7276
    Prev
    Next
    INDEX
    Explanations

    references to a specific technology company

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "HP" in various contexts

    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
    taboola
    -0.76
    notations
    -0.72
    ĸļ
    -0.70
    ãĤª
    -0.68
    PsyNetMessage
    -0.66
     Eston
    -0.65
    rontal
    -0.65
    horn
    -0.64
     Finnish
    -0.64
    Interstitial
    -0.64
    POSITIVE LOGITS
     Lovecraft
    1.16
     Pavilion
    0.98
    ilipp
    0.91
    ython
    0.86
    iencies
    0.83
    HP
    0.82
    erity
    0.81
    oenix
    0.81
    rint
    0.78
    olitics
    0.76
    Activations Density 0.017%

    No Known Activations