INDEX

Explanations

references to length 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 @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Offisielt

-0.82

 esetben

-0.78

 ſte

-0.78

GIP

-0.73

umumkan

-0.73

 Cabot

-0.72

 stomat

-0.70

jectures

-0.70

wój

-0.70

 yoksa

-0.70

POSITIVE LOGITS

 length

1.94

length

1.81

Length

1.74

 Length

1.72

 LENGTH

1.66

LENGTH

1.60

 lengths

1.51

getLength

1.42

长度

1.35

 lenght

1.33

Activations Density 0.094%

references to length in various contexts

No Comments

No Known Activations