© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 7556
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "anthrax"

    oai_token-act-pair · gpt-3.5-turbo

    references to anthrax and related terms

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

    No Comments

    Negative Logits
    VICE
    -0.91
    Assembly
    -0.74
    UTION
    -0.73
     Undead
    -0.72
    SPONSORED
    -0.71
    ABLE
    -0.71
     Galile
    -0.69
     guiActiveUnfocused
    -0.68
    FORMATION
    -0.66
    LOAD
    -0.66
    POSITIVE LOGITS
    rax
    1.43
    opoulos
    1.11
    ropy
    1.03
     anth
    1.03
    oine
    0.99
    ologies
    0.99
    anches
    0.92
    ony
    0.91
    rac
    0.89
    opl
    0.89
    Activations Density 0.012%

    No Known Activations