INDEX

Explanations

references to mortality or death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

archiviato

-0.67

urgis

-0.63

 >=",

-0.55

ьаж

-0.55

WriteTagHelper

-0.54

 ویکی‌پدی

-0.53

indd

-0.53

乓

-0.52

jug

-0.52

titial

-0.52

POSITIVE LOGITS

 flows

0.87

 Flows

0.79

 dying

0.78

 Dying

0.77

Flows

0.69

ViewImports

0.66

flows

0.66

Dying

0.66

relate

0.66

 seuls

0.64

Activations Density 0.138%

references to mortality or death

No Comments

No Known Activations