INDEX

Explanations

expressions of personal feelings and emotional states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Zeneca

-0.65

 scania

-0.64

umably

-0.64

További

-0.62

 RISERVATA

-0.62

Dữ

-0.61

FunctionFlags

-0.61

بوابة

-0.61

 otomatig

-0.61

ContentAsync

-0.60

POSITIVE LOGITS

 like

0.81

 compelled

0.67

 good

0.63

 sorry

0.60

 secure

0.60

secure

0.59

 obligated

0.59

bad

0.58

Hochspringen

0.58

 safe

0.57

Activations Density 0.061%

expressions of personal feelings and emotional states

No Comments

No Known Activations