© 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. 8-RES-JB
    11. 6452
    Prev
    Next
    INDEX
    Explanations

    specific keywords and phrases related to announcements, information, and directives

    oai_token-act-pair · gpt-3.5-turbo

    thematic elements related to announcements and setups for future actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.62
    ãĤ§
    -0.61
    ãĥİ
    -0.55
    alys
    -0.55
    sort
    -0.55
    uristic
    -0.54
    ãĤ¦ãĤ¹
    -0.53
    ãĤ¸
    -0.53
    capacity
    -0.52
    alysis
    -0.52
    POSITIVE LOGITS
     Panther
    0.64
     Mehran
    0.62
     America
    0.61
     Gators
    0.60
     Goldstein
    0.60
     Hancock
    0.59
     Ronnie
    0.59
     Dame
    0.59
     Colorado
    0.59
     Kazakh
    0.58
    Activations Density 1.704%

    No Known Activations