INDEX

Explanations

phrases that convey methods or processes

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

 Mahmud

-0.97

 насељу

-0.97

 Majefty

-0.96

 Monfieur

-0.94

Datuak

-0.94

 Schulte

-0.92

 McNeil

-0.91

 pleaſure

-0.90

ScreenState

-0.90

 preſent

-0.89

POSITIVE LOGITS

way

1.83

Way

1.82

WAY

1.78

 ways

1.67

Way

1.65

 Ways

1.61

way

1.53

 WAYS

1.51

Ways

1.46

WAY

1.39

Activations Density 0.086%

phrases that convey methods or processes

No Comments

No Known Activations