INDEX

Explanations

phrases related to illusions and delusions

oai_token-act-pair · gpt-3.5-turbo

terms related to illusions and misleading perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

secut

-0.67

Interstitial

-0.67

nan

-0.65

vez

-0.65

ippers

-0.64

ishops

-0.63

nard

-0.61

gars

-0.60

mins

-0.60

aches

-0.59

POSITIVE LOGITS

istically

1.05

ary

1.02

 illusion

0.98

ually

0.93

 illusions

0.92

 Illusion

0.92

ery

0.89

ibility

0.85

arial

0.83

ulence

0.83

Activations Density 0.032%

phrases related to illusions and delusions

terms related to illusions and misleading perceptions

No Comments

No Known Activations