INDEX

Explanations

terms related to organisms or living entities

oai_token-act-pair · gpt-3.5-turbo

references to living organisms and their behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 giveaways

-0.83

 voic

-0.82

 global

-0.82

 flip

-0.79

pun

-0.79

 junk

-0.78

 DRAG

-0.78

RIP

-0.78

 giveaway

-0.77

 cheesy

-0.75

POSITIVE LOGITS

une

1.35

 organism

1.27

 acquaintance

1.24

 agitated

1.24

 accustomed

1.19

 intercourse

1.18

 agitation

1.17

 discontent

1.16

 inflamm

1.14

 enterprises

1.11

Activations Density 0.107%

terms related to organisms or living entities

references to living organisms and their behaviors

No Comments

No Known Activations