INDEX

Explanations

reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate reasons or explanations

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

tle

-0.80

 ILCS

-0.78

bill

-0.75

wordpress

-0.74

sic

-0.72

raid

-0.71

bats

-0.70

iw

-0.70

Pred

-0.70

 jaws

-0.69

POSITIVE LOGITS

 mortals

0.79

 preferring

0.69

 fame

0.68

 reason

0.67

 executing

0.65

 variance

0.64

 reasons

0.63

 stopping

0.63

 canonical

0.63

 invalid

0.62

Activations Density 0.172%

reasons or explanations

phrases that indicate reasons or explanations

No Comments

No Known Activations