INDEX

Explanations

phrases associated with causation and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ImageContext

-0.82

<bos>

-0.66

 nonUne

-0.64

Portail

-0.61

はじめに

-0.60

InputBorder

-0.59

Rüyada

-0.59

ijų

-0.57

posedge

-0.54

彿

-0.54

POSITIVE LOGITS

 purpoſe

0.66

 myſelf

0.64

 itſelf

0.61

 Jefus

0.61

 raiſ

0.61

ſelf

0.60

hematical

0.59

 himſelf

0.58

 paſſ

0.57

Efq

0.57

Activations Density 0.739%

phrases associated with causation and processes

No Comments

No Known Activations