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. 6-RES-JB
    6. 19492
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    actions or efforts related to problem-solving and collaboration

    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
     summed
    -0.64
     consists
    -0.59
    hari
    -0.58
     refers
    -0.58
     understatement
    -0.56
     draped
    -0.56
    cember
    -0.56
    theless
    -0.55
    tumblr
    -0.54
     anecd
    -0.54
    POSITIVE LOGITS
    bia
    0.57
     viable
    0.56
     desired
    0.56
     safely
    0.55
     advantageous
    0.54
     urgently
    0.53
    heed
    0.53
     profitable
    0.52
    ]),
    0.51
     footing
    0.51
    Activations Density 1.135%

    No Known Activations