INDEX

Explanations

mentions of rules or regulations prohibiting certain actions

oai_token-act-pair · gpt-3.5-turbo

prohibitions and permissions regarding actions and behaviors

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

lves

-0.72

xon

-0.69

office

-0.67

 Soldier

-0.62

power

-0.59

tal

-0.59

posure

-0.59

leaf

-0.59

elect

-0.58

lish

-0.58

POSITIVE LOGITS

Reviewer

1.11

uthor

0.86

 exemptions

0.83

ptin

0.75

pedia

0.72

 allowed

0.70

 disclaim

0.70

 deviations

0.69

aston

0.69

 permitted

0.68

Activations Density 0.026%

mentions of rules or regulations prohibiting certain actions

prohibitions and permissions regarding actions and behaviors

No Comments

No Known Activations