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. 9-RES-JB
    6. 22229
    Prev
    Next
    INDEX
    Explanations

    phrases related to resistance or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conflict or resistance

    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
    catentry
    -0.72
    ients
    -0.70
     poisoning
    -0.64
    ilk
    -0.63
    £ı
    -0.60
     sped
    -0.58
     coma
    -0.58
    vous
    -0.58
     GDDR
    -0.58
    ascript
    -0.58
    POSITIVE LOGITS
     doorway
    0.80
    atoon
    0.78
    wark
    0.76
     solidarity
    0.71
    solid
    0.70
    ailable
    0.69
    arna
    0.68
    arius
    0.67
     defiance
    0.67
     entrance
    0.66
    Activations Density 0.117%

    No Known Activations