INDEX

Explanations

phrases containing the word "ams"

oai_token-act-pair · gpt-3.5-turbo

references to the term "ams" 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 @ 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

GROUND

-0.64

 hygiene

-0.61

 diabetes

-0.59

 scant

-0.59

 fluid

-0.58

 Gord

-0.58

 demographics

-0.58

PDATE

-0.57

 wart

-0.56

leans

-0.56

POSITIVE LOGITS

mith

1.01

hip

0.98

mas

0.94

hell

0.93

olver

0.93

sterdam

0.92

arah

0.91

utra

0.90

hed

0.89

icas

0.88

Activations Density 0.011%

phrases containing the word "ams"

references to the term "ams" in various contexts

No Comments

No Known Activations