INDEX

Explanations

references to the word "Stone"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Stone" 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 @ 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

oresc

-0.78

ership

-0.77

merce

-0.76

olulu

-0.73

ornia

-0.69

inen

-0.68

NCT

-0.67

unct

-0.66

Demand

-0.66

orescence

-0.66

POSITIVE LOGITS

hill

1.00

cold

0.95

falls

0.94

 Soup

0.88

fish

0.88

lake

0.87

castle

0.86

hen

0.85

 quar

0.84

works

0.83

Activations Density 0.039%

references to the word "Stone"

occurrences of the word "Stone" in various contexts

No Comments

No Known Activations