INDEX

Explanations

instances of the word "after" and its variations, indicating a focus on sequences of events or time progression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

Efq

-0.89

izowane

-0.85

rillation

-0.81

 Sarm

-0.75

ſelf

-0.75

Bronnen

-0.75

 Jefus

-0.74

GTI

-0.74

gdx

-0.74

 ویکی‌پدیای

-0.74

POSITIVE LOGITS

 After

1.01

 AFTER

0.94

AFTER

0.93

After

0.93

after

0.90

 after

0.87

 fter

0.84

)}(

0.76

Dopo

0.75

 Dopo

0.72

Activations Density 0.100%

instances of the word "after" and its variations, indicating a focus on sequences of events or time progression

No Comments

No Known Activations