INDEX

Explanations

instances of the word "have" followed by a number, possibly reflecting emphasis on possession or experience

oai_token-act-pair · gpt-3.5-turbo

the verb "have" 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

catentry

-0.69

hammer

-0.61

eal

-0.59

 prosecuting

-0.58

oshi

-0.58

 Voters

-0.57

 Apart

-0.57

tel

-0.57

esp

-0.57

—-

-0.57

POSITIVE LOGITS

 been

1.29

been

1.14

 gotten

1.10

 undergone

0.98

 Been

0.96

 gone

0.92

 done

0.88

drawn

0.88

 fallen

0.86

gotten

0.86

Activations Density 0.394%

instances of the word "have" followed by a number, possibly reflecting emphasis on possession or experience

the verb "have" in various contexts

No Comments

No Known Activations