INDEX

Explanations

words related to conflict and negative impacts like war, injury, disease, and danger

oai_token-act-pair · gpt-3.5-turbo

themes related to conflict, suffering, and moral implications of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 referen

-0.66

Liv

-0.62

ofi

-0.62

 Marketplace

-0.61

abase

-0.61

 trademark

-0.60

 Electoral

-0.59

Ri

-0.58

ynchron

-0.58

 Socket

-0.57

POSITIVE LOGITS

flies

0.97

killers

0.88

istically

0.86

bows

0.86

lessly

0.84

worms

0.83

lessness

0.82

bugs

0.82

seekers

0.82

ously

0.81

Activations Density 0.363%

words related to conflict and negative impacts like war, injury, disease, and danger

themes related to conflict, suffering, and moral implications of actions

No Comments

No Known Activations