INDEX

Explanations

phrases related to a specific location, possibly a town or point called "Whiskey."

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or geographic places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 DEFENSE

-0.71

ABE

-0.68

eering

-0.64

ļéĨĴ

-0.63

 traps

-0.62

alian

-0.62

 mileage

-0.62

 concessions

-0.61

 Factor

-0.60

 Opera

-0.60

POSITIVE LOGITS

ppers

1.12

ple

1.06

pper

1.05

ven

1.00

pped

0.98

pe

0.89

pling

0.88

plets

0.87

pes

0.86

cil

0.85

Activations Density 0.028%

phrases related to a specific location, possibly a town or point called "Whiskey."

references to specific locations or geographic places

No Comments

No Known Activations