© 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. 8176
    Prev
    Next
    INDEX
    Explanations

    words related to the action of removing or being deprived of something

    oai_token-act-pair · gpt-3.5-turbo
    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
    rious
    -0.83
     Correspond
    -0.77
    ANI
    -0.73
    QB
    -0.72
    ENTS
    -0.70
    OPER
    -0.69
    =-=-=-=-=-=-=-=-
    -0.68
    VERTIS
    -0.68
     Heavenly
    -0.67
    Ale
    -0.66
    POSITIVE LOGITS
     stripping
    1.17
     stripped
    1.08
    onite
    0.88
     naked
    0.82
    utic
    0.81
    utics
    0.80
     aback
    0.78
     hairc
    0.78
    jit
    0.78
     strips
    0.78
    Activations Density 0.011%

    No Known Activations