INDEX

Explanations

adjectives related to descriptive words, often ending with 'ing'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ad" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĨĴ

-0.68

 sclerosis

-0.66

 Lovecraft

-0.60

ANGE

-0.60

ALT

-0.60

 Marketplace

-0.60

 backwards

-0.60

 Constantin

-0.60

assetsadobe

-0.60

Ago

-0.59

POSITIVE LOGITS

visor

1.05

urai

1.01

rill

1.01

venture

0.97

onna

0.96

icate

0.95

itionally

0.95

ventures

0.94

illac

0.93

vance

0.93

Activations Density 0.048%

adjectives related to descriptive words, often ending with 'ing'

occurrences of the word "ad" in various forms

No Comments

No Known Activations