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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17602
    Prev
    Next
    INDEX
    Explanations

    mentions of legislations and laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to public health and safety issues

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

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.33
    ãĥ¼ãĥ³
    -0.28
    代
    -0.27
     outwe
    -0.26
    etta
    -0.26
    ãĤ´ãĥ³
    -0.26
    hazard
    -0.24
    uable
    -0.24
    ãĥĻ
    -0.24
    ãĥĩãĤ£
    -0.24
    POSITIVE LOGITS
     DRAGON
    0.23
     ..........
    0.22
     DARK
    0.22
    uzzle
    0.21
     Planes
    0.21
     Pv
    0.20
    terness
    0.19
     Capture
    0.19
     Reve
    0.19
     AS
    0.18
    Activations Density 10.873%

    No Known Activations