INDEX

Explanations

proper nouns, specifically names and locations

oai_token-act-pair · gpt-3.5-turbo

specific names and references related to individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 saline

-0.74

NXT

-0.72

 Juven

-0.67

hips

-0.66

 Escape

-0.64

 Newfoundland

-0.63

 eSports

-0.63

 Vikings

-0.63

 Wolves

-0.63

 cheek

-0.62

POSITIVE LOGITS

unta

1.01

Aj

0.99

adesh

0.99

ihara

0.97

ibl

0.96

afia

0.96

ulia

0.95

urai

0.93

ihad

0.93

iral

0.91

Activations Density 0.018%

proper nouns, specifically names and locations

specific names and references related to individuals or organizations

No Comments

No Known Activations