INDEX

Explanations

reported speech and attributions within text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

TagHelper

-0.75

 privées

-0.73

enderror

-0.68

IsContent

-0.65

SBATCH

-0.63

 religieuses

-0.62

 onCreateView

-0.60

 religieuse

-0.60

الصفحه

-0.58

tagHelper

-0.57

POSITIVE LOGITS

 said

1.11

 says

1.00

 Says

0.94

 stated

0.92

 remarked

0.91

وأضاف

0.88

 explained

0.87

 Said

0.84

said

0.84

 cautioned

0.84

Activations Density 0.431%

reported speech and attributions within text

No Comments

No Known Activations