INDEX

Explanations

symbols or representations that hold significant meanings

oai_token-act-pair · gpt-3.5-turbo

words related to symbolism and representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

INC

-0.65

 redistributed

-0.65

 servicing

-0.64

 conducted

-0.63

packing

-0.62

ienne

-0.62

ilyn

-0.61

 averaged

-0.60

 accounted

-0.60

 disag

-0.59

POSITIVE LOGITS

 Humanity

0.73

rium

0.70

thood

0.67

 Mata

0.66

ãĤ¨ãĥ«

0.65

 Guilty

0.65

 humanity

0.64

utf

0.64

 Mori

0.64

 masculinity

0.63

Activations Density 0.212%

symbols or representations that hold significant meanings

words related to symbolism and representations

No Comments

No Known Activations