INDEX

Explanations

repeated characters or symbols, particularly focusing on variations of accented letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 '\\;'

-0.94

》.

-0.89

*/}

-0.80

#:

-0.75

 bezeichneter

-0.75

oa̍t

-0.74

 tartalomajánló

-0.74

بوابة

-0.71

/*

-0.71

SequentialGroup

-0.70

POSITIVE LOGITS

â

2.05

â

1.90

Â

1.25

lâ

1.25

Â

1.24

Câ

1.18

lâ

1.09

Mâ

1.06

Bâ

1.05

câ

1.05

Activations Density 0.203%

repeated characters or symbols, particularly focusing on variations of accented letters

No Comments

No Known Activations