INDEX

Explanations

verbs and nouns related to traps

oai_token-act-pair · gpt-3.5-turbo

references to traps, both literal and metaphorical

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Roberts

-0.80

worth

-0.75

apps

-0.70

Ecc

-0.69

Ã«

-0.68

 Wikimedia

-0.67

 Doctors

-0.67

aucas

-0.66

Wid

-0.65

eni

-0.65

POSITIVE LOGITS

 trap

4.12

 traps

3.23

trap

3.12

 Trap

2.48

 trapping

2.25

 Traps

2.15

 bait

1.41

 ambush

1.37

 lure

1.30

 trapped

1.21

Activations Density 0.025%

verbs and nouns related to traps

references to traps, both literal and metaphorical

No Comments

No Known Activations