INDEX

Explanations

names of individuals, particularly focusing on law enforcement, legal, and business contexts

oai_token-act-pair · gpt-3.5-turbo

proper names, specifically those of individuals involved in professional or legal 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ´ãĤ¡

-0.82

ModLoader

-0.80

acters

-0.78

ãĤŃ

-0.69

minus

-0.66

à¨

-0.66

Ire

-0.65

AAAAAAAA

-0.64

ï¸

-0.64

aspberry

-0.63

POSITIVE LOGITS

etti

0.86

III

0.85

 oversaw

0.82

Jr

0.81

 convened

0.78

wark

0.78

 alerted

0.77

zinski

0.76

gren

0.76

 Baird

0.76

Activations Density 0.211%

names of individuals, particularly focusing on law enforcement, legal, and business contexts

proper names, specifically those of individuals involved in professional or legal contexts

No Comments

No Known Activations