INDEX

Explanations

phrases related to attributing actions or qualities to individuals

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "have"

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

hammer

-0.66

 Apart

-0.62

esp

-0.61

catentry

-0.60

 Voters

-0.60

Arc

-0.60

ocol

-0.59

eal

-0.59

tel

-0.59

oshi

-0.56

POSITIVE LOGITS

 been

1.35

been

1.22

 gotten

1.12

 Been

1.02

 undergone

1.02

 done

0.93

 gone

0.92

 fallen

0.91

 become

0.90

 begun

0.87

Activations Density 0.461%

phrases related to attributing actions or qualities to individuals

forms of the verb "have"

No Comments

No Known Activations