INDEX

Explanations

instances of the word "saw."

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

 exposure

-0.94

 exposures

-0.91

 EXPOSURE

-0.88

 Exposure

-0.87

Exposed

-0.85

exposure

-0.85

 exposed

-0.85

Exposure

-0.80

exposed

-0.80

 Exposed

-0.78

POSITIVE LOGITS

 runner

0.88

saw

0.84

saw

0.81

 runners

0.80

Saw

0.79

Saw

0.75

ToAction

0.73

 Baillargeon

0.73

 Runner

0.73

Runner

0.70

Activations Density 0.037%

instances of the word "saw."

No Comments

No Known Activations