INDEX

Explanations

references to familial relationships, particularly focusing on siblings, nephews, and nieces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

‗

-0.64

 Colchester

-0.60

 Nobel

-0.56

AnimationFrame

-0.56

breadcrumbs

-0.53

iterran

-0.53

STC

-0.53

timmen

-0.52

 globe

-0.52

 Infiniti

-0.51

POSITIVE LOGITS

 nephews

1.77

 nieces

1.58

 nephew

1.51

 niece

1.36

MigrationBuilder

1.06

 uncles

1.04

 aunt

1.02

 aunts

1.00

 uncle

0.98

 cousins

0.98

Activations Density 0.057%

references to familial relationships, particularly focusing on siblings, nephews, and nieces

No Comments

No Known Activations