INDEX

Explanations

elements of structured data or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Rec

-0.55

ívar

-0.54

iliary

-0.52

autique

-0.52

ceptre

-0.51

kháu

-0.51

ंदीखरीदारी

-0.51

onor

-0.48

flasche

-0.48

 Beecher

-0.47

POSITIVE LOGITS

ViewImports

0.65

reszcie

0.62

InputTagHelper

0.62

Etc

0.61

 Audiodateien

0.60

 uska

0.59

matchCondition

0.57

出版年

0.57

etc

0.56

greenrobot

0.55

Activations Density 0.444%

elements of structured data or code

No Comments

No Known Activations