© 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. 20100
    Prev
    Next
    INDEX
    Explanations

    people's names or terms related to "Gross" or "grossly" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Gross" and related variations

    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
    FUL
    -0.82
    */(
    -0.68
     fluor
    -0.62
    plates
    -0.61
    soDeliveryDate
    -0.61
    knife
    -0.60
     bearer
    -0.60
     clerk
    -0.60
    pires
    -0.60
    oused
    -0.59
    POSITIVE LOGITS
     Gross
    1.06
    cre
    0.79
    sein
    0.79
    utenberg
    0.79
    galitarian
    0.77
    mans
    0.75
    lander
    0.74
    eto
    0.73
    gross
    0.72
    enstein
    0.72
    Activations Density 0.006%

    No Known Activations