INDEX

Explanations

instances of the word "of" followed by another word

oai_token-act-pair · gpt-3.5-turbo

the phrase "of" followed by quantifiers or numerals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

WER

-0.76

 condem

-0.71

 surpr

-0.70

irection

-0.62

heit

-0.61

 agre

-0.61

 ende

-0.60

cape

-0.60

ensual

-0.59

helle

-0.59

POSITIVE LOGITS

dozen

0.67

userc

0.65

 dozen

0.63

arching

0.62

 whom

0.61

 Thousand

0.61

thood

0.60

 continents

0.58

arb

0.58

tein

0.57

Activations Density 0.089%

instances of the word "of" followed by another word

the phrase "of" followed by quantifiers or numerals

No Comments

No Known Activations