INDEX

Explanations

letters and their associated rankings or grades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 ioutil

-0.90

onOptions

-0.66

 Vikipedi

-0.64

日閲覧

-0.64

 tread

-0.63

彿

-0.60

makeText

-0.60

etheless

-0.59

tvguidetime

-0.59

 useDispatch

-0.58

POSITIVE LOGITS

PerformLayout

0.59

0.57

0.56

 AssemblyCulture

0.56

 Paglinawan

0.55

amoan

0.54

 EClass

0.53

piram

0.53

verwijspagina

0.53

SharedDtor

0.53

Activations Density 0.701%

letters and their associated rankings or grades

No Comments

No Known Activations