INDEX

Explanations

phrases indicating continuation or ongoing action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "continued."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oster

-0.99

ard

-0.85

arta

-0.82

ramid

-0.80

liest

-0.77

ranch

-0.73

ards

-0.73

atana

-0.72

ainted

-0.72

ustomed

-0.72

POSITIVE LOGITS

 unab

0.88

 depress

0.73

 onward

0.72

 proble

0.70

 tremend

0.69

ap

0.68

 onwards

0.66

 exha

0.65

 thrust

0.65

 sclerosis

0.65

Activations Density 0.033%

phrases indicating continuation or ongoing action

instances of the word "continued."

No Comments

No Known Activations