INDEX

Explanations

concepts related to uncertainty and ambiguity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.60

mpion

-0.53

Grand

-0.52

UpperCase

-0.48

grand

-0.47

 Grand

-0.47

 lievito

-0.47

WriteTagHelper

-0.47

heben

-0.46

 engaged

-0.46

POSITIVE LOGITS

 unclear

1.06

 mystery

1.04

mystery

0.98

 mysteries

0.95

 mysterious

0.92

 vague

0.90

 Uncertainty

0.90

 uncertainty

0.89

 confusing

0.87

 uncertain

0.87

Activations Density 0.494%

concepts related to uncertainty and ambiguity

No Comments

No Known Activations