INDEX

Explanations

phrases related to reading and written content

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

Jegyzetek

-0.56

 aceptas

-0.53

XmlAccessType

-0.50

makedirs

-0.48

 createSprite

-0.48

neri

-0.47

ioneers

-0.47

getDefault

-0.47

coda

-0.47

ellis

-0.47

POSITIVE LOGITS

 read

1.87

 reads

1.86

 reading

1.84

read

1.65

 readings

1.60

 Reads

1.57

 Reading

1.56

reading

1.53

Reading

1.53

 READ

1.49

Activations Density 0.150%

phrases related to reading and written content

No Comments

No Known Activations