INDEX

Explanations

phrases and words related to input handling in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.75

tory

-0.73

es

-0.69

tale

-0.64

-0.61

ture

-0.56

gory

-0.56

tative

-0.56

tation

-0.56

-0.53

POSITIVE LOGITS

nnnn

0.86

ned

0.85

ning

0.84

nnn

0.78

 kasarigan

0.76

RenderAtEndOf

0.72

 متعلقه

0.72

 незавершена

0.68

 ***!

0.67

はじめに

0.65

Activations Density 0.378%

phrases and words related to input handling in programming

No Comments

No Known Activations