INDEX

Explanations

phrases related to error messages or system notifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 brancas

-0.69

 colgantes

-0.62

 kasarigan

-0.60

 manna

-0.58

ValueStyle

-0.58

[++

-0.56

 Jurí

-0.56

 vermelhas

-0.55

gyű

-0.55

 '\\;'

-0.54

POSITIVE LOGITS

 AssemblyTitle

0.76

日閲覧

0.73

Архівовано

0.69

raf

0.68

OrBuilder

0.67

بوابة

0.66

Ware

0.66

价比

0.66

SOUNDBITE

0.65

قایناق‌لار

0.65

Activations Density 0.039%

phrases related to error messages or system notifications

No Comments

No Known Activations