INDEX

Explanations

references to rankings and statistics related to performance and achievement in various 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

 مرئيه

-0.69

voorbeeld

-0.64

ValueGeneration

-0.63

Organisateur

-0.59

 transfieras

-0.58

 Propag

-0.57

 kiệm

-0.57

tanleria

-0.57

ξει

-0.56

csolódó

-0.55

POSITIVE LOGITS

 ranked

1.28

 topped

1.13

 ranking

1.09

 topping

1.03

 ranks

1.01

 rank

1.00

 Ranked

0.94

 finishing

0.94

 finished

0.93

ranked

0.93

Activations Density 0.233%

references to rankings and statistics related to performance and achievement in various contexts

No Comments

No Known Activations