© 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. 2-RES-JB
    11. 17794
    Prev
    Next
    INDEX
    Explanations

    negative descriptions or critiques

    oai_token-act-pair · gpt-3.5-turbo

    words related to vilification and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cropped
    -0.67
    hr
    -0.65
     newsp
    -0.61
    print
    -0.60
     hearty
    -0.60
    Self
    -0.60
     Sevent
    -0.60
    Publisher
    -0.59
     Requ
    -0.59
    Ģ
    -0.58
    POSITIVE LOGITS
    vil
    1.06
    icious
    0.86
    chio
    0.84
    ibrary
    0.81
    ionage
    0.80
    theless
    0.79
    zx
    0.79
     Nadu
    0.78
     destro
    0.78
    arge
    0.77
    Activations Density 0.006%

    No Known Activations