INDEX

Explanations

instances of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

berdayakan

-0.81

 disambiguazione

-0.79

<unused52>

-0.77

<unused68>

-0.77

<unused3>

-0.77

<unused16>

-0.76

<unused21>

-0.76

<unused14>

-0.76

<unused79>

-0.76

[@BOS@]

-0.76

POSITIVE LOGITS

 continuing

0.69

 continued

0.66

 continue

0.63

 ongoing

0.62

continue

0.60

 continues

0.59

 продолжа

0.54

 Continuing

0.51

continuing

0.50

off

0.48

Activations Density 0.070%

instances of the word "on."

No Comments

No Known Activations