© 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. 11-RES-JB
    11. 3596
    Prev
    Next
    INDEX
    Explanations

    phrases related to removal or elimination

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of 'removal' or 'elimination' of various issues or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilant
    -0.78
    meet
    -0.74
    step
    -0.74
    ebus
    -0.74
    Result
    -0.73
    lake
    -0.72
     onwards
    -0.69
    ruary
    -0.66
    update
    -0.65
    venture
    -0.65
    POSITIVE LOGITS
     pesky
    1.23
     barriers
    1.21
     stigma
    1.09
     veil
    1.08
     offending
    1.08
     obsolete
    1.07
     inhib
    1.05
     unwanted
    1.02
     redundant
    1.01
     superflu
    1.00
    Activations Density 0.317%

    No Known Activations