INDEX

Explanations

mentions or references to the company Google

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Google" and identify sections relating to it

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

mble

-0.84

alid

-0.73

urst

-0.71

quez

-0.71

icka

-0.69

swing

-0.66

rift

-0.65

bil

-0.64

lain

-0.64

ivari

-0.64

POSITIVE LOGITS

plex

1.04

 Fiber

1.03

 Maps

0.99

 Doodle

0.93

 Lunar

0.90

 Chrome

0.89

 Glass

0.89

 Apps

0.88

 Analytics

0.85

Maps

0.84

Activations Density 0.024%

mentions or references to the company Google

occurrences of the word "Google" and identify sections relating to it

No Comments

No Known Activations