INDEX

Explanations

relationships of influence between different entities or events

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate cause-and-effect relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ntax

-0.65

utenberg

-0.63

ilion

-0.63

 Croat

-0.61

ntil

-0.61

 blat

-0.60

 shenan

-0.59

perty

-0.59

 Challenger

-0.58

requency

-0.56

POSITIVE LOGITS

 incentiv

0.74

 leads

0.74

 embold

0.73

 prompts

0.72

 creates

0.72

èĥ

0.69

 inspires

0.68

 encourages

0.68

 contributes

0.67

 generates

0.67

Activations Density 0.030%

relationships of influence between different entities or events

phrases that indicate cause-and-effect relationships

No Comments

No Known Activations