INDEX

Explanations

references to the financial institution AIG

oai_token-act-pair · gpt-3.5-turbo

references to the insurance industry and associated entities

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

etheless

-0.86

theless

-0.76

ozy

-0.72

bidden

-0.69

ength

-0.69

Mub

-0.68

 Shore

-0.66

 Machina

-0.65

idential

-0.65

liness

-0.65

POSITIVE LOGITS

arettes

1.01

GER

0.99

arette

0.98

gers

0.94

raphics

0.91

rams

0.90

uez

0.89

vernment

0.88

IG

0.88

INAL

0.86

Activations Density 0.010%

references to the financial institution AIG

references to the insurance industry and associated entities

No Comments

No Known Activations