INDEX

Explanations

structures and operations related to data mapping and entries in programming contexts

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

BeginContext

-0.89

addCriterion

-0.86

+:+

-0.82

 doubtnut

-0.79

UrlResolution

-0.78

 purpoſe

-0.78

 photolibrary

-0.77

SharedDtor

-0.76

+#+#

-0.76

Efq

-0.75

POSITIVE LOGITS

keys

0.79

 keys

0.70

Keys

0.61

values

0.60

 values

0.56

keySet

0.54

 Keys

0.51

key

0.50

Values

0.50

 KEYS

0.46

Activations Density 0.095%

structures and operations related to data mapping and entries in programming contexts

No Comments

No Known Activations