INDEX

Explanations

references to concrete materials and related concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 vastaan

-0.41

 ympä

-0.41

 становника

-0.40

 laaj

-0.40

 avanzado

-0.40

 käyt

-0.40

 nakalista

-0.40

 liitty

-0.38

niksi

-0.37

duos

-0.37

POSITIVE LOGITS

1.01

concrete

0.70

 synthèse

0.63

 concrete

0.60

 béton

0.59

Concrete

0.59

 cement

0.59

 Skate

0.58

dirt

0.58

Skate

0.58

Activations Density 1.947%

references to concrete materials and related concepts

No Known Activations