INDEX

Explanations

actions or events that have occurred or are happening

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Manifest

-0.82

 intimid

-0.64

 Williamson

-0.61

 rains

-0.57

 Citiz

-0.56

/+

-0.56

 Articles

-0.55

 Unle

-0.55

natureconservancy

-0.55

 Ecology

-0.55

POSITIVE LOGITS

now

1.26

 hindsight

0.98

 remembered

0.96

now

0.94

 nowadays

0.93

 recollection

0.90

 presently

0.90

NOW

0.87

 regrets

0.85

 currently

0.83

Activations Density 0.889%

actions or events that have occurred or are happening

No Comments

No Known Activations