INDEX

Explanations

code snippets and programming-related constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.47

pin

-0.47

toHexString

-0.46

leg

-0.45

 Plan

-0.45

-0.43

Ger

-0.43

igne

-0.43

sin

-0.42

POSITIVE LOGITS

 Roskov

0.80

soort

0.79

 дописавши

0.79

 архивлан

0.78

 AspNetCore

0.73

 الدولى

0.72

 Monfieur

0.72

Efq

0.71

 OFDb

0.71

 gainera

0.71

Activations Density 0.090%

code snippets and programming-related constructs

No Comments

No Known Activations