INDEX

Explanations

phrases indicating superlative or extreme experiences

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

SequentialGroup

-0.63

middels

-0.54

 Femen

-0.53

MENAFN

-0.53

andExpect

-0.53

 Pues

-0.52

 Głów

-0.51

zeciw

-0.50

bouncycastle

-0.49

canActivate

-0.49

POSITIVE LOGITS

 Roskov

0.65

 Marr

0.61

 actionBar

0.60

SaveChangesAsync

0.58

effort

0.56

 ever

0.55

 Normdatei

0.55

 BitSet

0.55

zke

0.54

 برانيه

0.54

Activations Density 0.074%

phrases indicating superlative or extreme experiences

No Comments

No Known Activations