INDEX

Explanations

phrases related to food toppings or ingredients

oai_token-act-pair · gpt-3.5-turbo

words or terms related to mozzarella or cheese products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĪĴ

-1.07

Ö¼

-0.67

COMPLE

-0.65

 prelim

-0.62

 Forth

-0.61

BIT

-0.61

 subp

-0.59

 stroke

-0.58

©¶æ

-0.57

wcs

-0.57

POSITIVE LOGITS

uddin

0.89

gow

0.75

lein

0.74

asonic

0.74

inho

0.73

iland

0.73

ipedia

0.69

gov

0.69

ensen

0.68

hesive

0.68

Activations Density 0.089%

phrases related to food toppings or ingredients

words or terms related to mozzarella or cheese products

No Comments

No Known Activations