© 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. 18820
    Prev
    Next
    INDEX
    Explanations

    words expressing strong emotions, such as disgust, panic, and happiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or exasperation

    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
     Devils
    -0.74
    oted
    -0.68
    Winged
    -0.64
     Petra
    -0.63
     davidjl
    -0.61
     ledger
    -0.60
     orig
    -0.59
     condensed
    -0.59
     Belarus
    -0.59
     Butterfly
    -0.56
    POSITIVE LOGITS
    ugh
    1.02
    resses
    0.91
    ftime
    0.86
    bread
    0.81
    ties
    0.80
    umin
    0.80
    culosis
    0.79
    ricane
    0.79
    rowth
    0.79
    pin
    0.79
    Activations Density 0.029%

    No Known Activations