INDEX

Explanations

words related to poisoning

oai_token-act-pair · gpt-3.5-turbo

terms related to poisoning and intoxication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ney

-0.75

book

-0.74

neys

-0.67

books

-0.67

ties

-0.66

opher

-0.66

frame

-0.65

objects

-0.65

bor

-0.65

ational

-0.64

POSITIVE LOGITS

emia

1.01

elsius

0.93

osis

0.86

ptoms

0.82

 Prevention

0.80

 prevention

0.78

 poisoning

0.77

 sickness

0.75

 hemor

0.72

icter

0.72

Activations Density 0.045%

words related to poisoning

terms related to poisoning and intoxication

No Comments

No Known Activations