© 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. 7-RES-JB
    11. 20034
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "vert" or "verted"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "vert" and its variations or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.81
     Bei
    -0.71
    çĦ
    -0.71
    utical
    -0.69
    Aw
    -0.68
    senal
    -0.67
    ptive
    -0.66
    accompan
    -0.64
    ateur
    -0.63
    Interstitial
    -0.62
    POSITIVE LOGITS
    ibility
    1.00
    verted
    0.94
    version
    0.90
    icals
    0.87
    ophobia
    0.87
    verts
    0.83
    ibly
    0.83
    orial
    0.83
    ected
    0.78
    ible
    0.77
    Activations Density 0.029%

    No Known Activations