© 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. 2-RES-JB
    11. 20898
    Prev
    Next
    INDEX
    Explanations

    phrases or names containing the word "vo"

    oai_token-act-pair · gpt-3.5-turbo

    the term "vo" in various contexts, indicating a focus on specific references or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Else
    -0.75
     Arrows
    -0.72
     towels
    -0.70
    ģ«
    -0.66
     foundations
    -0.65
    papers
    -0.62
     iPads
    -0.61
    taker
    -0.61
    İĭ
    -0.61
     Lisp
    -0.60
    POSITIVE LOGITS
    vo
    0.99
    orde
    0.97
    pload
    0.95
    ilo
    0.90
    onte
    0.89
    VO
    0.86
    oice
    0.84
    iced
    0.84
    ices
    0.84
    apor
    0.82
    Activations Density 0.005%

    No Known Activations