INDEX

Explanations

quantitative measures of agreement or disagreement regarding beliefs and attitudes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

älde

-0.51

gug

-0.48

روابط

-0.45

INV

-0.43

expandindo

-0.43

Inv

-0.43

不怕

-0.43

 proprement

-0.42

anik

-0.42

usty

-0.42

POSITIVE LOGITS

 agree

3.28

 agrees

2.97

 agreeing

2.82

 agreed

2.79

 Agree

2.76

 agreement

2.75

agree

2.71

Agree

2.59

agreed

2.52

 Agreed

2.41

Activations Density 0.625%

quantitative measures of agreement or disagreement regarding beliefs and attitudes

No Comments

No Known Activations