INDEX

Explanations

phrases that classify and describe specific subjects and topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

WithIOException

-0.77

 hjem

-0.60

GraphicsUnit

-0.58

ⓘ

-0.56

numerusform

-0.52

thâu

-0.52

########.

-0.52

MessageTagHelper

-0.52

ponenten

-0.51

cloudfront

-0.51

POSITIVE LOGITS

 matter

1.69

matter

1.62

Matter

1.36

 Matter

1.35

 MATTER

1.29

matters

0.86

 matters

0.85

 matière

0.75

 Matters

0.72

 mater

0.70

Activations Density 0.153%

phrases that classify and describe specific subjects and topics

No Comments

No Known Activations