INDEX

Explanations

references to citations and academic validation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

its

-1.05

Its

-0.91

 яке

-0.90

Its

-0.89

 Оно

-0.82

its

-0.81

 которое

-0.81

它

-0.78

它的

-0.78

it

-0.72

POSITIVE LOGITS

 celles

1.25

 herself

1.20

 ones

1.12

 lesquelles

1.08

herself

1.00

 ellas

0.99

Elles

0.96

she

0.92

 éstas

0.90

 Elles

0.88

Activations Density 0.035%

references to citations and academic validation

No Comments

No Known Activations