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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9-RES-JB
    6. 16875
    Prev
    Next
    INDEX
    Explanations

    expressions indicating regret or should-have-done-something-differently situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "should have" indicating regret or reflection on past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocol
    -0.60
     hostage
    -0.58
    owicz
    -0.56
    ori
    -0.56
    note
    -0.55
    Mem
    -0.54
    onse
    -0.53
     enchant
    -0.53
    isms
    -0.52
     waning
    -0.52
    POSITIVE LOGITS
     gotten
    1.19
     been
    1.07
     waited
    1.07
    been
    1.04
     listened
    1.04
     stayed
    1.00
     avoided
    0.95
     acted
    0.94
     gone
    0.92
     intervened
    0.92
    Activations Density 0.052%

    No Known Activations