INDEX

Explanations

instances of repetition or return phrases in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Thereafter

-0.46

attles

-0.42

PRS

-0.42

seg

-0.41

brun

-0.41

 deshalb

-0.41

 initState

-0.41

국

-0.41

culata

-0.41

ropho

-0.41

POSITIVE LOGITS

こちらも

1.20

bootstrapcdn

0.99

 again

0.93

Again

0.93

 szint

0.93

これも

0.91

 Again

0.88

同样

0.88

同樣

0.87

again

0.86

Activations Density 0.478%

instances of repetition or return phrases in the text

No Comments

No Known Activations