INDEX

Explanations

phrases related to statistical observations and features within datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

SOM

-0.49

octanol

-0.48

 geste

-0.48

 Celui

-0.47

<!--[

-0.47

Suffix

-0.45

quic

-0.44

United

-0.44

EventEmitter

-0.44

 gutem

-0.44

POSITIVE LOGITS

 pairs

0.84

 pair

0.78

hasMoreElements

0.77

 Administrativna

0.70

 combinaison

0.69

 paire

0.65

 possible

0.64

GraphicsUnit

0.63

 AssemblyTitle

0.63

 Roskov

0.62

Activations Density 1.159%

phrases related to statistical observations and features within datasets

No Comments

No Known Activations