© 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. 17751
    Prev
    Next
    INDEX
    Explanations

    phrases related to removal, deletion, or elimination

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of erasure or removal

    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
    anooga
    -0.95
    annis
    -0.94
    uay
    -0.88
    Kind
    -0.67
    aquin
    -0.67
    apache
    -0.66
    enegger
    -0.66
    croft
    -0.66
    egal
    -0.65
    ingham
    -0.65
    POSITIVE LOGITS
     erase
    1.16
     erased
    0.91
    asures
    0.75
     Doodle
    0.75
    brush
    0.73
    chwitz
    0.70
     Jagu
    0.68
     overwrite
    0.67
     scars
    0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.67
    Activations Density 0.011%

    No Known Activations