INDEX

Explanations

references to the term "Anonymous", which could relate to the group, the concept of anonymity, or the term used as a placeholder

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Anonymous" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Gork

-0.88

eele

-0.76

enegger

-0.72

 Blasio

-0.71

lot

-0.70

ushing

-0.68

++++++++++++++++

-0.68

=-=-=-=-=-=-=-=-

-0.67

efully

-0.66

meaning

-0.65

POSITIVE LOGITS

 Anonymous

0.75

TERN

0.74

 obliged

0.72

uthor

0.71

ica

0.71

 hacker

0.68

stration

0.67

 infiltrated

0.64

Party

0.63

ãĥĩ

0.62

Activations Density 0.013%

references to the term "Anonymous", which could relate to the group, the concept of anonymity, or the term used as a placeholder

occurrences of the word "Anonymous" in various contexts

No Comments

No Known Activations