INDEX

Explanations

references to cognitive functions and cognitive-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

брь

-0.64

findpost

-0.63

 MotionEvent

-0.60

élie

-0.60

dersfield

-0.58

MotionEvent

-0.57

差不

-0.56

 الحره

-0.56

Arty

-0.55

subpackage

-0.55

POSITIVE LOGITS

{'

0.74

 cognitive

0.72

 itſelf

0.69

 Cognitive

0.68

lee

0.64

Cognitive

0.62

cognitive

0.60

 doubtnut

0.58

 Ashley

0.57

 themſelves

0.56

Activations Density 0.182%

references to cognitive functions and cognitive-related terms

No Comments

No Known Activations