INDEX

Explanations

the concept of illusions

oai_token-act-pair · gpt-3.5-turbo

terms related to illusions and delusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Interstitial

-0.73

annis

-0.65

vez

-0.64

 Issues

-0.63

poon

-0.63

MIT

-0.63

ippers

-0.63

Discussion

-0.60

 Conduct

-0.60

nard

-0.59

POSITIVE LOGITS

istically

1.07

ually

1.04

 illusion

1.02

ary

0.89

ously

0.89

mir

0.88

istical

0.88

 Illusion

0.85

 illusions

0.84

arial

0.82

Activations Density 0.015%

the concept of illusions

terms related to illusions and delusions

No Comments

No Known Activations