INDEX

Explanations

references to different types of poison

oai_token-act-pair · gpt-3.5-turbo

terms related to poison and toxic substances

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

noon

-0.87

irc

-0.76

blance

-0.75

ann

-0.74

planned

-0.70

dar

-0.68

stand

-0.67

den

-0.67

AMA

-0.66

arel

-0.65

POSITIVE LOGITS

 poisoning

1.22

 poison

1.15

 poisoned

1.08

 dart

1.02

 poisonous

0.98

 arsenic

0.87

 darts

0.87

 poisons

0.86

 antidote

0.85

gas

0.85

Activations Density 0.015%

references to different types of poison

terms related to poison and toxic substances

No Comments

No Known Activations