INDEX

Explanations

words related to titles or names with the word "Big" in them

oai_token-act-pair · gpt-3.5-turbo

references to prominent figures and brands associated with "Big" 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

xit

-0.71

ajor

-0.70

pta

-0.64

tmp

-0.64

owder

-0.64

isconsin

-0.62

CET

-0.61

psc

-0.60

isode

-0.59

 Published

-0.58

POSITIVE LOGITS

Thumbnail

0.73

(>

0.68

 Bust

0.68

 è£ıè

0.67

 lumber

0.66

ructose

0.66

gie

0.65

————————

0.65

 Bundle

0.64

elson

0.64

Activations Density 0.101%

words related to titles or names with the word "Big" in them

references to prominent figures and brands associated with "Big" in various contexts

No Comments

No Known Activations