INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Alice" and related contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emate

-0.83

iaries

-0.82

eful

-0.80

itching

-0.80

eling

-0.78

els

-0.78

ework

-0.77

aries

-0.75

ifying

-0.75

er

-0.74

POSITIVE LOGITS

xon

0.91

 Cooper

0.90

Alice

0.72

 Wonderland

0.70

vana

0.69

 Royale

0.68

pheus

0.67

hammer

0.67

BUG

0.65

 retri

0.63

Activations Density 0.069%

people's names

mentions of the name "Alice" and related contexts

No Comments

No Known Activations