© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 2768
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that challenge or contradict common beliefs or narratives

    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
    oleon
    -0.79
    ilitating
    -0.78
    ramid
    -0.77
    killer
    -0.73
    artney
    -0.73
    anus
    -0.73
    arij
    -0.73
    hens
    -0.72
    ahime
    -0.71
    liam
    -0.70
    POSITIVE LOGITS
     notwithstanding
    0.89
     contrary
    0.84
    SPONSORED
    0.79
    ptions
    0.77
    etheless
    0.73
     guiActiveUn
    0.72
    ly
    0.72
    CLASSIFIED
    0.70
     untrue
    0.69
     affirm
    0.69
    Activations Density 0.016%

    No Known Activations