© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17167
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise or disappointment

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orage
    -0.81
    aukee
    -0.74
    ead
    -0.73
    iaz
    -0.69
    iHUD
    -0.67
    zman
    -0.66
    æĿ
    -0.66
    abase
    -0.65
    ield
    -0.65
    aura
    -0.65
    POSITIVE LOGITS
     someone
    0.90
     somebody
    0.86
     anyone
    0.80
     they
    0.78
    someone
    0.78
     we
    0.74
     anybody
    0.71
     nobody
    0.70
    soever
    0.70
    rely
    0.67
    Activations Density 0.111%

    No Known Activations