INDEX

Explanations

references to science fiction themes or elements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Planet" and its associations in a context

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

OUT

-0.76

ilant

-0.75

rown

-0.74

ugh

-0.73

displayText

-0.73

shire

-0.72

ãģĦ

-0.72

thens

-0.71

initions

-0.71

Interstitial

-0.69

POSITIVE LOGITS

eers

1.02

arium

0.99

 Parenthood

0.98

 Planet

0.92

 Pharma

0.91

 Fitness

0.89

ciating

0.85

 Eater

0.83

 Hulk

0.82

 Stronghold

0.81

Activations Density 0.020%

references to science fiction themes or elements

occurrences of the word "Planet" and its associations in a context

No Comments

No Known Activations