INDEX

Explanations

prepositional phrases indicating location

oai_token-act-pair · gpt-3.5-turbo

phrases containing the word "under."

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

eln

-0.69

iterranean

-0.66

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.66

 Begins

-0.65

utenberg

-0.65

************

-0.63

mov

-0.63

ennial

-0.62

ILY

-0.62

ãĥ£

-0.60

POSITIVE LOGITS

neath

1.12

pins

0.94

oos

0.89

dogs

0.89

whelming

0.88

cuts

0.87

pants

0.86

ĸļ

0.84

lining

0.84

Ļ½

0.84

Activations Density 0.047%

prepositional phrases indicating location

phrases containing the word "under."

No Comments

No Known Activations