INDEX

Explanations

phrases related to event organization or planning

oai_token-act-pair · gpt-3.5-turbo

the occurrence of repetitive references to "Organ 2."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

nces

-0.63

req

-0.62

ILLE

-0.62

teen

-0.61

 Cheney

-0.60

ered

-0.60

rior

-0.60

erred

-0.59

PLIED

-0.58

ï¸ı

-0.58

POSITIVE LOGITS

izational

1.71

isations

1.53

izations

1.43

izers

1.33

izer

1.27

isers

1.20

izes

1.19

ized

1.16

ically

1.13

ization

1.12

Activations Density 0.048%

phrases related to event organization or planning

the occurrence of repetitive references to "Organ 2."

No Comments

No Known Activations