INDEX

Explanations

proper nouns and names of people or characters

oai_token-act-pair · gpt-3.5-turbo

articles and descriptors that introduce characters or subjects in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĥ¯

-0.79

 alike

-0.71

 outper

-0.66

Ub

-0.65

ulo

-0.65

reviewed

-0.64

 headquartered

-0.64

 alas

-0.63

ttle

-0.61

 thereto

-0.60

POSITIVE LOGITS

 impending

0.76

oneliness

0.71

usterity

0.70

Semitism

0.70

onym

0.69

record

0.67

ĻĤ

0.66

antically

0.65

 importance

0.65

 potential

0.64

Activations Density 0.585%

proper nouns and names of people or characters

articles and descriptors that introduce characters or subjects in narratives

No Comments

No Known Activations