INDEX

Explanations

words related to deterrence, including both the concept and its various implementations

oai_token-act-pair · gpt-3.5-turbo

terms related to deterrence and its effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ebus

-0.82

oln

-0.80

gres

-0.74

orted

-0.72

rote

-0.71

umo

-0.71

olen

-0.71

elf

-0.70

ugen

-0.70

ucket

-0.69

POSITIVE LOGITS

 deterrent

1.54

 deterrence

1.14

 disadvant

0.82

 discour

0.79

 deter

0.78

 destro

0.78

 barriers

0.78

 reinforcement

0.77

 barrier

0.76

 dissu

0.76

Activations Density 0.008%

words related to deterrence, including both the concept and its various implementations

terms related to deterrence and its effectiveness

No Comments

No Known Activations