INDEX

Explanations

mentions of the name "Cho" followed by numerical values suggesting importance or relevance

oai_token-act-pair · gpt-3.5-turbo

the name "Cho" and its variations

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

doors

-0.83

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.65

 EntityItem

-0.64

working

-0.64

Reloaded

-0.63

night

-0.63

 IMAGES

-0.62

RANT

-0.61

master

-0.61

sburg

-0.60

POSITIVE LOGITS

osing

1.17

oser

1.05

ices

1.03

pper

1.00

osen

0.97

ppy

0.95

pped

0.90

oses

0.90

iral

0.87

ppa

0.86

Activations Density 0.010%

mentions of the name "Cho" followed by numerical values suggesting importance or relevance

the name "Cho" and its variations

No Comments

No Known Activations