INDEX

Explanations

terms related to inappropriate, harmful, or unethical actions

oai_token-act-pair · gpt-3.5-turbo

terms related to abusive and unethical behavior

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

electric

-0.79

pop

-0.74

rition

-0.68

ellar

-0.67

soType

-0.66

oret

-0.63

arro

-0.61

ICA

-0.61

grown

-0.60

soDeliveryDate

-0.60

POSITIVE LOGITS

 perpetrated

1.01

 inflicted

0.90

 incurred

0.90

 towards

0.86

 misconduct

0.83

 committed

0.83

 crimes

0.83

 dealings

0.81

 whatsoever

0.81

 harming

0.80

Activations Density 0.174%

terms related to inappropriate, harmful, or unethical actions

terms related to abusive and unethical behavior

No Comments

No Known Activations