INDEX

Explanations

references to memory and remembrance, particularly in the context of grief or loss

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

+#+#

-0.53

LookAnd

-0.49

 gustar

-0.47

PropTypes

-0.46

葺

-0.44

يديا

-0.43

siv

-0.42

yled

-0.42

 susceptibles

-0.42

 aank

-0.42

POSITIVE LOGITS

 missed

0.97

 Missed

0.88

 sorely

0.84

Missed

0.82

 חיצוניים

0.75

missed

0.74

 remembered

0.74

twimg

0.73

 miss

0.70

 greatly

0.69

Activations Density 0.080%

references to memory and remembrance, particularly in the context of grief or loss

No Comments

No Known Activations