INDEX

Explanations

verbs that indicate hesitation or reversal of action

oai_token-act-pair · gpt-3.5-turbo

words related to being hindered or obstructed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

holder

-0.68

 Sheen

-0.67

 ÙĪ

-0.66

 Rite

-0.65

Northern

-0.63

×

-0.62

======

-0.62

Interstitial

-0.61

Ø³

-0.59

 magnification

-0.59

POSITIVE LOGITS

aling

1.00

agog

0.94

asus

0.90

ped

0.90

iatric

0.89

acles

0.88

aled

0.88

iped

0.87

insula

0.87

erson

0.86

Activations Density 0.011%

verbs that indicate hesitation or reversal of action

words related to being hindered or obstructed

No Comments

No Known Activations