INDEX

Explanations

phrases related to taking advantage of situations or other individuals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating exploitation or taking advantage of situations or individuals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

earchers

-0.88

ignt

-0.78

cci

-0.75

usa

-0.71

execute

-0.71

cade

-0.71

allion

-0.71

heading

-0.71

ordering

-0.71

 dstg

-0.69

POSITIVE LOGITS

 loopholes

1.10

 opportunities

1.07

 opportunity

1.00

 loophole

0.89

 vulnerabilities

0.77

 existing

0.76

 deductions

0.73

 exemptions

0.72

 tricks

0.71

 protections

0.71

Activations Density 0.070%

phrases related to taking advantage of situations or other individuals

phrases indicating exploitation or taking advantage of situations or individuals

No Comments

No Known Activations