INDEX

Explanations

references to specific organizations or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to governmental and institutional entities

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

mble

-0.67

 Morty

-0.65

 Indra

-0.64

»Ĵ

-0.63

 Lanka

-0.63

bnb

-0.60

Berry

-0.59

hots

-0.59

 Chand

-0.58

 Brett

-0.57

POSITIVE LOGITS

's

1.01

wide

0.85

ÃŃs

0.85

 involvement

0.77

 needing

0.69

 motto

0.66

Â´

0.63

 propensity

0.63

 playbook

0.63

 willingness

0.63

Activations Density 0.728%

references to specific organizations or entities

proper nouns related to governmental and institutional entities

No Comments

No Known Activations