INDEX

Explanations

names or variations of the name "Dominique."

oai_token-act-pair · gpt-3.5-turbo

references to the word "unique"

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

anger

-0.75

dfx

-0.75

itably

-0.72

TPPStreamerBot

-0.72

ough

-0.70

coming

-0.70

owment

-0.70

angers

-0.68

izoph

-0.68

mable

-0.67

POSITIVE LOGITS

ique

0.94

eers

0.90

nil

0.83

eer

0.79

 Royale

0.78

Vie

0.74

 Franc

0.68

vre

0.67

urs

0.67

ira

0.67

Activations Density 0.028%

names or variations of the name "Dominique."

references to the word "unique"

No Comments

No Known Activations