INDEX

Explanations

adjectives or terms expressing extremity or intensity

oai_token-act-pair · gpt-3.5-turbo

descriptors of intensity or extremity in various contexts

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

anders

-0.79

ploma

-0.70

ADS

-0.66

andering

-0.65

APH

-0.65

aden

-0.64

annis

-0.64

antics

-0.64

conservancy

-0.63

adr

-0.61

POSITIVE LOGITS

ly

2.89

LY

1.85

liness

1.41

lys

1.37

fully

1.33

lies

1.30

ELY

1.27

edly

1.20

liest

1.15

ity

1.09

Activations Density 0.173%

adjectives or terms expressing extremity or intensity

descriptors of intensity or extremity in various contexts

No Comments

No Known Activations