INDEX

Explanations

phrases indicating restrictions, limitations, or disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 câteva

-0.64

 sometime

-0.63

 almeno

-0.60

 Slightly

-0.60

 slightly

-0.59

SOME

-0.58

slightly

-0.58

MessageTagHelper

-0.58

somewhat

-0.58

 puțin

-0.57

POSITIVE LOGITS

yet

0.76

yet

0.74

YET

0.64

Yet

0.62

Yet

0.62

 necessarily

0.59

 harmed

0.59

contentLoaded

0.58

necessarily

0.56

 exceed

0.56

Activations Density 0.817%

phrases indicating restrictions, limitations, or disclaimers

No Comments

No Known Activations