INDEX

Explanations

phrases related to uncertainty or lack of knowledge

oai_token-act-pair · gpt-3.5-turbo

references to unspecified or ambiguous information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

boa

-0.86

ickr

-0.85

utic

-0.83

odcast

-0.82

phasis

-0.81

igsaw

-0.80

bourg

-0.79

iffs

-0.79

ongyang

-0.78

onest

-0.78

POSITIVE LOGITS

theless

0.86

 quantity

0.83

 unknown

0.81

 Mortal

0.81

Origin

0.80

erness

0.73

 jurisdiction

0.71

terday

0.69

 Unknown

0.69

 territory

0.68

Activations Density 0.015%

phrases related to uncertainty or lack of knowledge

references to unspecified or ambiguous information

No Comments

No Known Activations