INDEX

Explanations

legal or official terms related to policies and regulations

oai_token-act-pair · gpt-3.5-turbo

conditional statements related to political or legal contexts

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

 wonders

-0.64

avery

-0.63

 wonder

-0.63

anon

-0.63

ADS

-0.58

inho

-0.58

DragonMagazine

-0.58

 Lines

-0.57

 amazed

-0.57

 Whitman

-0.56

POSITIVE LOGITS

 sufficiently

0.89

 otherwise

0.87

 sufficient

0.74

or

0.69

 enough

0.69

 properly

0.67

 reasonably

0.64

 lapse

0.64

mission

0.63

 adequate

0.62

Activations Density 0.676%

legal or official terms related to policies and regulations

conditional statements related to political or legal contexts

No Comments

No Known Activations