INDEX

Explanations

phrases related to distance, progress, or achievement

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a journey or progress towards a goal

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

SPONSORED

-0.86

ghazi

-0.84

Dialogue

-0.74

mobi

-0.69

-0.67

CI

-0.65

Sources

-0.64

PLA

-0.63

Article

-0.62

 Narr

-0.62

POSITIVE LOGITS

 underest

0.87

 overdue

0.72

 hindsight

0.71

 Kuro

0.71

sighted

0.70

 turnaround

0.70

orrow

0.68

 admire

0.68

 coincidence

0.68

 understatement

0.67

Activations Density 0.434%

phrases related to distance, progress, or achievement

phrases indicating a journey or progress towards a goal

No Comments

No Known Activations