INDEX

Explanations

phrases indicating limits or conditions that should not be exceeded

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Getenv

-0.61

 perus

-0.56

olsom

-0.56

MZ

-0.55

Jai

-0.55

tableFuture

-0.55

ńcz

-0.54

anyahu

-0.54

räger

-0.54

Pvt

-0.54

POSITIVE LOGITS

 exceed

1.15

 exceeding

1.06

 exceeded

1.02

 exceeds

0.95

 виправивши

0.74

 dépass

0.72

 surpassing

0.69

 damn

0.68

 damned

0.68

 превы

0.68

Activations Density 0.046%

phrases indicating limits or conditions that should not be exceeded

No Comments

No Known Activations