INDEX

Explanations

phrases with the structure "is set to."

oai_token-act-pair · gpt-3.5-turbo

phrases indicating planned actions or scheduled events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inventoryQuantity

-0.82

issance

-0.76

ilee

-0.73

Strength

-0.73

aud

-0.65

imilation

-0.64

Sense

-0.64

obbies

-0.62

 Souls

-0.62

eatures

-0.62

POSITIVE LOGITS

tle

0.90

estone

0.88

tering

0.87

 forth

0.87

tered

0.85

abl

0.82

ters

0.80

itud

0.80

ter

0.74

offs

0.73

Activations Density 0.033%

phrases with the structure "is set to."

phrases indicating planned actions or scheduled events

No Comments

No Known Activations