INDEX

Explanations

coordination-related terms and actions

oai_token-act-pair · gpt-3.5-turbo

references to the concept of coordination

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 ageing

-0.78

Sil

-0.77

livion

-0.73

wall

-0.72

 Ashes

-0.70

sil

-0.69

 Syndrome

-0.68

Myth

-0.67

 Patt

-0.66

 laps

-0.66

POSITIVE LOGITS

 coordinate

3.70

 coordinates

2.99

 Coord

2.10

coord

2.06

 coord

2.06

 coordinating

1.85

ordinate

1.58

 coordinated

1.41

 coordination

1.19

 coordin

1.14

Activations Density 0.032%

coordination-related terms and actions

references to the concept of coordination

No Comments

No Known Activations