INDEX

Explanations

phrases related to product features and material properties

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

AndEndTag

-0.74

lapsingToolbar

-0.73

OrWhiteSpace

-0.71

RenderAtEndOf

-0.65

imanapun

-0.64

DEAR

-0.62

Bibliografía

-0.59

 EconPapers

-0.59

jspb

-0.58

HasBeenSet

-0.56

POSITIVE LOGITS

 ensures

1.17

 ensuring

1.01

 assures

0.93

 ensure

0.92

 guaranteeing

0.89

 provides

0.89

 allows

0.87

 guarantees

0.85

 makes

0.85

 delivers

0.83

Activations Density 0.211%

phrases related to product features and material properties

No Comments

No Known Activations