INDEX

Explanations

instances of the word "remember" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

twimg

-0.77

ficial

-0.71

 dAtA

-0.68

$")

-0.65

égorie

-0.63

 endregion

-0.63

 acred

-0.63

styleType

-0.63

richlet

-0.62

 unknownFields

-0.62

POSITIVE LOGITS

 remembered

1.72

 remember

1.68

 remembering

1.65

 remembers

1.62

 Remember

1.54

Remember

1.52

remember

1.51

 Remembering

1.47

 REMEMBER

1.45

 memory

1.35

Activations Density 0.113%

instances of the word "remember" and its variations

No Comments

No Known Activations