INDEX

Explanations

differentiating factors or comparisons between entities

oai_token-act-pair · gpt-3.5-turbo

comparative phrases that emphasize differences between entities or phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Reloaded

-0.64

Sec

-0.61

ãĤī

-0.60

orum

-0.60

 Ambro

-0.60

appropriately

-0.60

mble

-0.60

mint

-0.59

èĢħ

-0.57

Enough

-0.57

POSITIVE LOGITS

 counterparts

0.59

amide

0.57

cept

0.55

erest

0.54

landers

0.53

00200000

0.53

hod

0.53

 disclaim

0.52

 kinderg

0.52

 wont

0.52

Activations Density 0.229%

differentiating factors or comparisons between entities

comparative phrases that emphasize differences between entities or phenomena

No Comments

No Known Activations