INDEX

Explanations

phrases indicating potential or hypothetical actions or situations

oai_token-act-pair · gpt-3.5-turbo

variations of the verb "to be."

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

 Ples

-0.74

rating

-0.70

ashtra

-0.66

 Kills

-0.65

rador

-0.63

ivity

-0.62

OVA

-0.62

Ã¡n

-0.62

oleon

-0.60

rats

-0.60

POSITIVE LOGITS

yond

0.76

gotten

0.71

ãĤ´ãĥ³

0.65

ilet

0.62

here

0.62

reprene

0.62

twe

0.61

BF

0.60

erent

0.58

ievers

0.56

Activations Density 0.024%

phrases indicating potential or hypothetical actions or situations

variations of the verb "to be."

No Comments

No Known Activations