INDEX

Explanations

details related to competitive sports events and achievements

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

原始内容存档于

-0.61

arily

-0.58

GraphicsUnit

-0.56

 everyday

-0.56

protoimpl

-0.56

principalTable

-0.55

Xna

-0.55

Rohy

-0.54

Dichloropropane

-0.53

OrCreate

-0.53

POSITIVE LOGITS

 beating

0.75

 defeating

0.74

 thanks

0.71

 against

0.71

 after

0.69

 graças

0.68

 usai

0.67

 nadat

0.67

 devant

0.64

 despite

0.64

Activations Density 0.241%

details related to competitive sports events and achievements

No Comments

No Known Activations