INDEX

Explanations

expressions indicating thoughts or memories of experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

__':

-0.66

__':

-0.62

 насељу

-0.60

setVerticalGroup

-0.57

Efq

-0.51

Personendaten

-0.51

Faça

-0.50

ArgsConstructor

-0.50

 Theſe

-0.49

 onAnimation

-0.49

POSITIVE LOGITS

 comes

1.32

 come

1.20

 springs

1.17

 immediately

1.17

 spring

1.11

 Comes

1.06

immediately

1.06

comes

1.04

 Come

1.01

Immediately

1.01

Activations Density 0.138%

expressions indicating thoughts or memories of experiences

No Comments

No Known Activations