INDEX

Explanations

statements or quotes made by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of reported speech or quotes

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

otype

-0.73

Hung

-0.70

Pont

-0.70

Photos

-0.70

pee

-0.68

Ale

-0.67

à¦

-0.66

icum

-0.65

Lens

-0.64

phthal

-0.63

POSITIVE LOGITS

 goodbye

0.86

 moreover

0.85

 furthermore

0.77

 bluntly

0.70

 Cosponsors

0.69

 secondly

0.68

 emphatically

0.67

 afterward

0.66

 afterwards

0.66

 therefore

0.65

Activations Density 0.210%

statements or quotes made by individuals

instances of reported speech or quotes

No Comments

No Known Activations