INDEX

Explanations

significant phrases related to job-related inquiries or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

opath

-0.49

**)

-0.47

)._

-0.47

__]

-0.47

Un

-0.44

jsonwebtoken

-0.43

weta

-0.42

Un

-0.42

{/

-0.42

 richesse

-0.41

POSITIVE LOGITS

KURZBESCHREIBUNG

0.77

AddTagHelper

0.76

 FetchType

0.74

ьаж

0.70

 ویکی‌پدیا

0.68

ImageContext

0.66

 snippetHide

0.65

WriteTagHelper

0.65

uxxxx

0.64

 propOrder

0.64

Activations Density 0.195%

significant phrases related to job-related inquiries or descriptions

No Comments

No Known Activations