INDEX

Explanations

mentions of comfort and comfort-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 giudi

-0.79

Jad

-0.74

Mills

-0.73

InstrumentedTest

-0.72

CodeAttribute

-0.71

PathVariable

-0.71

 Cipher

-0.71

ArrowToggle

-0.70

 Mills

-0.69

BeginContext

-0.68

POSITIVE LOGITS

Comfort

1.17

Comfortable

1.13

 Comfort

1.11

 comfort

1.11

 COMFORT

1.08

comfort

1.08

fortable

1.06

 comfortable

1.03

comfortable

1.01

 comforts

0.99

Activations Density 0.041%

mentions of comfort and comfort-related concepts

No Comments

No Known Activations