INDEX

Explanations

phrases indicating a recommendation or suggestion

oai_token-act-pair · gpt-3.5-turbo

phrases indicating expectations or recommendations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GGGGGGGG

-0.67

 Syndrome

-0.65

ZI

-0.64

 Chains

-0.63

atile

-0.62

 Resistance

-0.62

ITED

-0.62

 Puzzle

-0.60

LP

-0.60

reality

-0.60

POSITIVE LOGITS

 ideally

1.06

be

0.99

ered

0.93

 clarify

0.83

 strive

0.81

ering

0.80

bes

0.80

 behave

0.79

othal

0.78

 theoretically

0.77

Activations Density 0.059%

phrases indicating a recommendation or suggestion

phrases indicating expectations or recommendations

No Comments

No Known Activations