INDEX

Explanations

words related to mitigating risks or issues

oai_token-act-pair · gpt-3.5-turbo

terms related to reducing or mitigating risks and negative impacts

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

olds

-0.87

swick

-0.83

letter

-0.82

whe

-0.80

corn

-0.78

NAS

-0.77

sters

-0.76

eters

-0.71

ker

-0.71

ession

-0.70

POSITIVE LOGITS

 mitigation

0.94

 mitigate

0.88

atively

0.86

 inconven

0.84

 variance

0.83

00200000

0.83

 damages

0.80

 damage

0.80

 immunity

0.76

 effects

0.76

Activations Density 0.078%

words related to mitigating risks or issues

terms related to reducing or mitigating risks and negative impacts

No Comments

No Known Activations