INDEX

Explanations

phrases related to diet and nutrition

oai_token-act-pair · gpt-3.5-turbo

references to diet

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Dam

-0.71

 Morse

-0.68

Pon

-0.66

 bidding

-0.65

 Templar

-0.63

 Stra

-0.62

Constructed

-0.61

Ort

-0.61

 Patterson

-0.60

 Avalon

-0.60

POSITIVE LOGITS

eteria

1.12

etics

1.10

rition

1.08

etic

1.06

onut

1.03

 diet

1.00

oleon

0.98

etically

0.97

namese

0.95

 Coke

0.88

Activations Density 0.016%

phrases related to diet and nutrition

references to diet

No Comments

No Known Activations