INDEX

Explanations

patterns of comparison and similarity among subjects

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

Separate

-0.76

 separate

-0.76

 Separate

-0.73

separate

-0.69

 separately

-0.69

 terpisah

-0.65

eroon

-0.64

 separado

-0.64

 FetchType

-0.64

Individual

-0.63

POSITIVE LOGITS

 similarities

0.82

 common

0.82

 similarity

0.82

same

0.72

 similar

0.71

 shared

0.71

Same

0.70

 identical

0.67

共通

0.66

 Same

0.66

Activations Density 0.484%

patterns of comparison and similarity among subjects

No Comments

No Known Activations