INDEX

Explanations

Mars-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of Mars and its significance

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

istical

-0.70

elist

-0.70

oshop

-0.68

uncture

-0.67

Hispanic

-0.66

ibus

-0.65

erate

-0.65

ocard

-0.64

 CARD

-0.63

-----------

-0.62

POSITIVE LOGITS

 Rover

1.09

 Mars

0.97

 Orbit

0.84

 rover

0.81

alis

0.80

 Exploration

0.78

 Misty

0.76

 colonists

0.74

den

0.73

Mars

0.71

Activations Density 0.011%

Mars-related terms

mentions of Mars and its significance

No Comments

No Known Activations