INDEX

Explanations

occurrences of the word "been" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

has

-0.87

woordig

-0.59

 كومونز

-0.56

годня

-0.55

tedì

-0.55

umbuhan

-0.54

lidays

-0.54

 possui

-0.54

is

-0.54

ülés

-0.54

POSITIVE LOGITS

 hadn

0.81

帖最后由

0.76

 habían

0.75

had

0.70

 avaient

0.67

 vardı

0.66

 Había

0.65

Notae

0.64

OGND

0.62

Had

0.62

Activations Density 0.127%

occurrences of the word "been" in various contexts

No Comments

No Known Activations