INDEX

Explanations

descriptions of characters in a narrative context

oai_token-act-pair · gpt-3.5-turbo

descriptive nouns and phrases that characterize individuals and their roles

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

views

-0.92

atories

-0.91

olutions

-0.89

ispers

-0.87

 VIDEOS

-0.86

AMS

-0.83

orders

-0.81

cation

-0.78

encies

-0.77

estyles

-0.77

POSITIVE LOGITS

 blonde

1.15

 nurse

1.14

 young

1.12

 girl

1.12

 waitress

1.11

 handsome

1.10

 woman

1.10

 classmate

1.10

 charismatic

1.10

 blond

1.09

Activations Density 0.312%

descriptions of characters in a narrative context

descriptive nouns and phrases that characterize individuals and their roles

No Comments

No Known Activations