INDEX

Explanations

descriptive words and phrases that highlight uniqueness and personality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 doInBackground

-0.83

SharedDtor

-0.82

AndEndTag

-0.76

WireFormatLite

-0.75

SharedCtor

-0.73

 setuptools

-0.71

 onCreateView

-0.70

rungsseite

-0.69

 raiſ

-0.67

Filmografie

-0.65

POSITIVE LOGITS

 charm

1.05

 flavor

1.01

 personality

0.96

 flavour

0.91

 flair

0.88

 soul

0.87

 charisma

0.85

 sparkle

0.85

 spirit

0.85

 depth

0.84

Activations Density 0.219%

descriptive words and phrases that highlight uniqueness and personality

No Comments

No Known Activations