INDEX

Explanations

expressions related to loss and regret

oai_token-act-pair · gpt-3.5-turbo

expressions of loss and permanence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ses

-0.66

ahime

-0.65

MpServer

-0.64

ĳå£«

-0.64

soType

-0.63

 largeDownload

-0.61

Newsletter

-0.59

iHUD

-0.58

edIn

-0.58

externalActionCode

-0.58

POSITIVE LOGITS

theless

1.29

 again

1.01

again

0.98

 EVER

0.98

 forgive

0.96

 underestimate

0.91

 admit

0.88

 regain

0.86

 cease

0.84

 forget

0.84

Activations Density 0.041%

expressions related to loss and regret

expressions of loss and permanence

No Comments

No Known Activations