INDEX

Explanations

words related to minimizing or reducing negative impacts or problems

oai_token-act-pair · gpt-3.5-turbo

terms related to risk reduction or mitigation strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ession

-0.78

ker

-0.71

ebus

-0.70

lished

-0.66

dom

-0.65

prints

-0.65

doms

-0.64

olds

-0.63

kie

-0.63

¦

-0.63

POSITIVE LOGITS

 mitigation

1.16

 mitigate

0.98

 remed

0.82

 mitigating

0.80

atives

0.79

 solutions

0.76

00200000

0.75

iation

0.74

igating

0.73

 inconven

0.72

Activations Density 0.024%

words related to minimizing or reducing negative impacts or problems

terms related to risk reduction or mitigation strategies

No Comments

No Known Activations