© 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. 7-RES-JB
    11. 17142
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the intensity of emotions or dedication

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neutral
    -0.63
     scraps
    -0.60
    bent
    -0.59
    raltar
    -0.58
    aldehyde
    -0.56
     shoots
    -0.56
    ½
    -0.54
     pairs
    -0.54
    winner
    -0.54
     vacated
    -0.53
    POSITIVE LOGITS
     compared
    0.73
    mouth
    0.71
    Interstitial
    0.68
    externalActionCode
    0.68
    hed
    0.67
    ]]
    0.66
    inventoryQuantity
    0.66
    ocating
    0.65
    dayName
    0.64
    !!!!!!!!
    0.63
    Activations Density 0.133%

    No Known Activations