INDEX

Explanations

proper nouns related to a specific entity abbreviated as "NR"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the acronym "NR" followed by various numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zai

-0.73

 Metatron

-0.70

Minecraft

-0.67

 Fairfax

-0.65

 Villa

-0.64

 Izan

-0.64

dates

-0.64

 seeded

-0.64

 Samoa

-0.63

 Tsarnaev

-0.63

POSITIVE LOGITS

NR

0.92

otiation

0.90

NR

0.90

emonic

0.89

UTH

0.88

ACK

0.85

CLE

0.82

 councill

0.79

rint

0.78

PN

0.77

Activations Density 0.009%

proper nouns related to a specific entity abbreviated as "NR"

occurrences of the acronym "NR" followed by various numbers

No Comments

No Known Activations