INDEX

Explanations

phrases or words referring to or mentioning something specific

oai_token-act-pair · gpt-3.5-turbo

phrases that involve references to specific topics or subjects

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

 laureate

-0.66

/#

-0.65

itte

-0.65

tumblr

-0.62

ãĥīãĥ©

-0.60

ethical

-0.58

unker

-0.58

osate

-0.58

ontent

-0.58

Ã¶n

-0.57

POSITIVE LOGITS

uations

0.69

gars

0.66

Nib

0.64

 Nieto

0.63

 quotations

0.63

Poe

0.61

ename

0.60

enegger

0.60

 sarcast

0.60

 referring

0.60

Activations Density 0.119%

phrases or words referring to or mentioning something specific

phrases that involve references to specific topics or subjects

No Comments

No Known Activations