INDEX

Explanations

assertions or expectations in a testing framework, indicating validation checks

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Хьажоргаш

-1.11

 '\\;'

-1.05

extAlignment

-1.02

 surla

-0.94

uxxxx

-0.91

LookAnd

-0.90

WindowConstants

-0.90



-0.89

jooq

-0.83

principalColumn

-0.82

POSITIVE LOGITS

expect

0.75

RSpec

0.65

assertThat

0.63

Mek

0.59

 coton

0.59

Naw

0.57

koning

0.56

tomie

0.55

 echi

0.55

 religieuses

0.53

Activations Density 0.006%

assertions or expectations in a testing framework, indicating validation checks

No Comments

No Known Activations