INDEX

Explanations

positive evaluations of people or situations

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

Negative Logits

 caucus

-0.84

hadiran

-0.84

 Serif

-0.80

osoba

-0.79

 Divina

-0.77

lern

-0.77

 Caucus

-0.77

InjectAttribute

-0.76

 declarat

-0.76

रण

-0.75

POSITIVE LOGITS

 good

1.60

 GOOD

1.57

good

1.56

GOOD

1.56

 Good

1.55

Good

1.51

 Goodwin

1.24

 Goodman

1.14

goods

0.98

 buena

0.95

Activations Density 0.060%

positive evaluations of people or situations

No Known Activations