INDEX

Explanations

terms related to acceleration and improvement in processes or mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Kariera

-0.81

 GenerationType

-0.75

 ujednoznacz

-0.74

ChildScrollView

-0.69

 EdgeInsets

-0.67

Chy

-0.66

ostomy

-0.65

enumi

-0.65

 confec

-0.65

 Goodwill

-0.64

POSITIVE LOGITS

rod

1.11

 Cafe

1.09

 rods

1.08

 cafe

1.08

 Rods

1.04

 Café

1.03

 cafes

1.01

Cafe

1.00

 arcs

0.99

cafe

0.99

Activations Density 0.097%

terms related to acceleration and improvement in processes or mechanisms

No Comments

No Known Activations