INDEX

Explanations

numbers related to addresses

oai_token-act-pair · gpt-3.5-turbo

numerical values, particularly those associated with measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

anooga

-0.77

hya

-0.70

querque

-0.70

 prem

-0.68

ifice

-0.67

istry

-0.66

amount

-0.65

 explanatory

-0.64

inery

-0.63

ilib

-0.62

POSITIVE LOGITS

.............

0.89

GMT

0.82

GMT

0.80

0.79

CTR

0.78

0.77

0.76

Activations Density 0.069%

numbers related to addresses

numerical values, particularly those associated with measurements or quantities

No Comments

No Known Activations