INDEX

Explanations

references to directory structures or file paths in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 berikut

-0.47

Prompt

-0.47

 notare

-0.46

 hinaus

-0.45

VersionUID

-0.42

gop

-0.40

<eos>

-0.40

 ओर

-0.40

 berupa

-0.39

 serupa

-0.39

POSITIVE LOGITS

sizeCache

0.91

 Paglinawan

0.88

 protoimpl

0.86

 Савезне

0.82

Билгалдахарш

0.81

 <=",

0.81

sidemargin

0.77

CompleteListener

0.76

ItemBackground

0.76

addCriterion

0.75

Activations Density 0.304%

references to directory structures or file paths in a coding context

No Comments

No Known Activations