INDEX

Explanations

terms related to medical, social, and political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Expert

-0.61

Expert

-0.59

migrationBuilder

-0.57

enumi

-0.57

itel

-0.56

 letters

-0.55

guten

-0.54

 Artem

-0.53

 رد

-0.53

hrte

-0.53

POSITIVE LOGITS

 financially

1.65

 medically

1.60

 physically

1.59

 psychologically

1.56

 spiritually

1.55

 politically

1.53

 musically

1.50

 academically

1.47

 mentally

1.45

 socially

1.45

Activations Density 0.298%

terms related to medical, social, and political contexts

No Comments

No Known Activations