© 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. 0-RES-JB
    11. 2921
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "CB" followed by a number ranging from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical or biological agents in the context of warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emo
    -0.84
    una
    -0.71
     lun
    -0.70
    untu
    -0.70
    Leaks
    -0.67
    urtles
    -0.66
    eli
    -0.66
    sei
    -0.65
    assic
    -0.65
     Homer
    -0.63
    POSITIVE LOGITS
     CB
    3.84
    CB
    2.49
     DT
    1.52
     LB
    1.46
     DB
    1.37
     WR
    1.37
     cannabinoid
    1.32
     RB
    1.29
     CF
    1.28
     CC
    1.27
    Activations Density 0.023%

    No Known Activations