INDEX

Explanations

the word "nuts" at varying activation levels

oai_token-act-pair · gpt-3.5-turbo

instances of the word "nuts" in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

pless

-0.70

naire

-0.65

nered

-0.64

âĢ¢âĢ¢âĢ¢âĢ¢

-0.64

 Cheong

-0.63

oping

-0.63

Anne

-0.61

lon

-0.61

âĢ¢âĢ¢

-0.60

LESS

-0.60

POSITIVE LOGITS

 nuts

1.24

ħĭ

0.96

 peanuts

0.85

mith

0.81

nuts

0.81

terday

0.78

nut

0.78

hots

0.75

 bacon

0.73

erker

0.71

Activations Density 0.008%

the word "nuts" at varying activation levels

instances of the word "nuts" in various contexts

No Known Activations