© 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. 1-RES-JB
    11. 23566
    Prev
    Next
    INDEX
    Explanations

    Keywords related to reduction or decrease

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reduce" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Found
    -0.84
    Origin
    -0.76
    Fight
    -0.73
    Dream
    -0.72
     Americas
    -0.70
    Member
    -0.70
    Written
    -0.69
    hold
    -0.69
    Country
    -0.68
    SN
    -0.68
    POSITIVE LOGITS
    uce
    0.98
     carbohyd
    0.94
    uces
    0.92
    xual
    0.88
    icides
    0.86
     reducing
    0.85
    mental
    0.84
     reduce
    0.83
    ministic
    0.83
     mitigation
    0.82
    Activations Density 0.022%

    No Known Activations