INDEX

Explanations

phrases or keywords related to the location "Las Vegas."

oai_token-act-pair · gpt-3.5-turbo

mentions of Las Vegas

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

skirts

-0.89

dit

-0.70

ORED

-0.68

 WARN

-0.67

 recip

-0.64

reads

-0.62

lessly

-0.62

smanship

-0.62

 guiActiveUnfocused

-0.61

framework

-0.61

POSITIVE LOGITS

 Vegas

1.06

 Lumpur

0.95

 Angeles

0.83

Rey

0.82

quet

0.82

agna

0.80

zman

0.80

etr

0.79

cano

0.78

ques

0.78

Activations Density 0.012%

phrases or keywords related to the location "Las Vegas."

mentions of Las Vegas

No Comments

No Known Activations