INDEX

Explanations

terms related to detection and assessment in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 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

msa

-0.57

 Bous

-0.56

:✨

-0.56

Marina

-0.56

 Marina

-0.54

 năm

-0.54

ſp

-0.54

multer

-0.51

 Gilmore

-0.51

 Dwyer

-0.51

POSITIVE LOGITS

detectChanges

0.60

 Detect

0.59

 detect

0.59

detect

0.57

 reação

0.57

 react

0.56

 surpresa

0.55

 reaction

0.54

 detección

0.53

 reaccion

0.50

Activations Density 0.305%

terms related to detection and assessment in various contexts

No Comments

No Known Activations

terms related to detection and assessment in various contexts

No Comments

No Known Activations