INDEX

Explanations

symbols and identifiers in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

withstanding

-0.85

которые

-0.84

-0.60

-0.59

-0.58

-0.56

giveness

-0.55

-0.54

POSITIVE LOGITS

featureID

0.80

хьтан

0.68

 Italijanski

0.59

IndentedString

0.59

 queſta

0.59

GD

0.58

 myſelf

0.57

HtmlAttribute

0.56

GN

0.56

ſelf

0.56

Activations Density 2.042%

symbols and identifiers in scientific or technical contexts

No Comments

No Known Activations