INDEX

Explanations

instances of the word "alt" or variations like "alted" and "alty."

oai_token-act-pair · gpt-3.5-turbo

words associated with various types of malt and alternative ingredients in food or beverages

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

Fuk

-0.91

lihood

-0.87

 Karin

-0.74

å£

-0.73

 Simulation

-0.70

HIP

-0.69

 Kuro

-0.68

©¶æ

-0.67

NCT

-0.67

manship

-0.66

POSITIVE LOGITS

itude

0.97

rition

0.92

icult

0.88

oad

0.88

agne

0.87

ravel

0.86

opol

0.85

anamo

0.85

antic

0.85

itudes

0.84

Activations Density 0.014%

instances of the word "alt" or variations like "alted" and "alty."

words associated with various types of malt and alternative ingredients in food or beverages

No Comments

No Known Activations