INDEX

Explanations

specific references to materials in a document, such as reports, articles, movies, or books

oai_token-act-pair · gpt-3.5-turbo

references to the term "the" as well as context related to infographics and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

heit

-0.79

atics

-0.70

ulence

-0.68

olicy

-0.67

arians

-0.66

rontal

-0.66

abiding

-0.65

istas

-0.64

agogue

-0.64

inx

-0.64

POSITIVE LOGITS

 context

1.10

 midst

0.93

 vicinity

0.92

 entirety

0.90

 aforementioned

0.88

 introductory

0.87

 preceding

0.85

 prol

0.85

 description

0.84

 article

0.84

Activations Density 0.259%

specific references to materials in a document, such as reports, articles, movies, or books

references to the term "the" as well as context related to infographics and reports

No Comments

No Known Activations