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. 6883
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing misguided actions or criticisms

    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
     stabilization
    -0.74
     nightly
    -0.73
    oother
    -0.66
    hedral
    -0.65
    winner
    -0.65
    stellar
    -0.65
    flix
    -0.65
    interrupted
    -0.64
    igree
    -0.64
     stabilized
    -0.64
    POSITIVE LOGITS
     omission
    0.95
     irresponsible
    0.86
     judgement
    0.79
     infer
    0.78
     cowardly
    0.78
     arrogance
    0.77
     coward
    0.77
     motives
    0.75
     hypocrisy
    0.74
     Stupid
    0.74
    Activations Density 0.406%

    No Known Activations