© 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. 8-RES-JB
    11. 20232
    Prev
    Next
    INDEX
    Explanations

    phrases related to removal or elimination

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to the removal or abolishment of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rium
    -0.74
    akening
    -0.69
    felt
    -0.64
    rings
    -0.64
    enegger
    -0.62
    eur
    -0.62
    fab
    -0.61
    ETF
    -0.61
    here
    -0.61
    NG
    -0.61
    POSITIVE LOGITS
    aneous
    0.94
    aneously
    0.78
    noxious
    0.76
     duplication
    0.76
    inators
    0.74
    ministic
    0.73
     redund
    0.69
    ication
    0.68
     needless
    0.67
     distractions
    0.66
    Activations Density 0.040%

    No Known Activations