INDEX

Explanations

phrases indicating uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or speculation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 PLUS

-0.80

 srfAttach

-0.76

chwitz

-0.71

EMA

-0.70

âĵĺ

-0.68

anger

-0.68

ACH

-0.65

rake

-0.64

 Aging

-0.63

Et

-0.62

POSITIVE LOGITS

 technically

1.09

 ostensibly

0.89

 initially

0.83

 differ

0.82

 theoretically

0.78

 admittedly

0.77

 somewhat

0.73

 vary

0.71

 anecd

0.68

 originally

0.67

Activations Density 0.436%

phrases indicating uncertainty or speculation

phrases indicating uncertainty or speculation

No Comments

No Known Activations