© 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. 23845
    Prev
    Next
    INDEX
    Explanations

    phrases that express feelings or emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional states and feelings

    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
    ilts
    -0.74
    licensed
    -0.71
    ondo
    -0.70
    taining
    -0.68
    xual
    -0.67
    eger
    -0.66
    etermination
    -0.64
     Alic
    -0.64
    ictions
    -0.64
    tions
    -0.64
    POSITIVE LOGITS
     awkward
    0.85
    MpServer
    0.80
     distinctly
    0.78
     awfully
    0.77
     like
    0.76
     hollow
    0.76
     oddly
    0.76
     differently
    0.75
     faintly
    0.75
     cramped
    0.74
    Activations Density 0.043%

    No Known Activations