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

    Neuronpedia

    APICircuit 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. 12-RES-JB
    6. 14689
    Prev
    Next
    INDEX
    Explanations

    legal case citations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numerical data and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     masculinity
    -0.71
     masks
    -0.65
     gaze
    -0.59
     researcher
    -0.59
    anguages
    -0.59
     watches
    -0.58
     praises
    -0.57
     mosques
    -0.57
    idays
    -0.57
     leads
    -0.56
    POSITIVE LOGITS
     Ct
    1.19
     Cir
    1.10
    Ct
    1.07
     ___
    0.98
     Civ
    0.96
     Supp
    0.96
     ¶
    0.94
     Crim
    0.92
    Arg
    0.91
     supra
    0.89
    Activations Density 0.044%

    No Known Activations