© 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. 1-RES-JB
    11. 8746
    Prev
    Next
    INDEX
    Explanations

    words related to excessive or sudden consumption

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to binge behavior or excessive consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CPC
    -0.68
    iona
    -0.68
    cule
    -0.65
    animous
    -0.64
    tes
    -0.64
    slow
    -0.61
    creation
    -0.61
    ourced
    -0.58
    drawn
    -0.57
    children
    -0.57
    POSITIVE LOGITS
    inge
    1.46
    inges
    0.80
    odox
    0.77
     Peaks
    0.76
    Aren
    0.75
    quartered
    0.75
    jriwal
    0.72
    arthed
    0.72
     advoc
    0.71
    assi
    0.70
    Activations Density 0.007%

    No Known Activations