INDEX

Explanations

phrases related to consequences and outcomes of actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

addPreferredGap

-0.51

 חיצוניים

-0.48

 entityManager

-0.46

Ier

-0.45

ghum

-0.44

 يست

-0.43

Rost

-0.43

 مقد

-0.43

HttpServlet

-0.43

virons

-0.42

POSITIVE LOGITS

effects

0.93

Effects

0.76

Consequences

0.75

 externi

0.74

 Effects

0.74

 effects

0.73

 consequence

0.71

effect

0.71

 ComVisible

0.69

 Folgen

0.67

Activations Density 0.385%

phrases related to consequences and outcomes of actions or events

No Comments

No Known Activations