INDEX

Explanations

proper nouns related to different locations with the word "Little" in them

oai_token-act-pair · gpt-3.5-turbo

references to "Little" in various contexts, possibly related to titles or names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

inates

-0.71

bach

-0.71

inator

-0.70

iety

-0.67

inators

-0.67

atically

-0.67

ILLE

-0.67

 polarized

-0.65

isible

-0.65

inate

-0.65

POSITIVE LOGITS

finger

1.03

 Mermaid

0.93

john

0.88

 Debbie

0.87

woods

0.86

 Havana

0.84

Things

0.81

 Pony

0.81

 Creatures

0.81

 Sister

0.80

Activations Density 0.017%

proper nouns related to different locations with the word "Little" in them

references to "Little" in various contexts, possibly related to titles or names

No Comments

No Known Activations