INDEX

Explanations

facts or pieces of information

oai_token-act-pair · gpt-3.5-turbo

various kinds of informative points or noteworthy details

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

ebook

-0.72

psc

-0.70

arus

-0.69

arez

-0.68

esi

-0.68

azo

-0.68

gur

-0.67

urated

-0.64

aline

-0.63

inder

-0.63

POSITIVE LOGITS

:-

0.90

 pertaining

0.86

 relating

0.78

":[{"

0.77

 regarding

0.73

 related

0.69

 glean

0.68

 glim

0.68

viz

0.68

 besides

0.67

Activations Density 0.274%

facts or pieces of information

various kinds of informative points or noteworthy details

No Comments

No Known Activations