INDEX

Explanations

words related to destruction or causing harm

oai_token-act-pair · gpt-3.5-turbo

instances of the word "destroy" and its variations

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

ETF

-0.87

annis

-0.76

liner

-0.73

çīĪ

-0.70

ature

-0.69

DragonMagazine

-0.65

 Demand

-0.64

culation

-0.64

aque

-0.63

legal

-0.63

POSITIVE LOGITS

 havoc

0.96

roying

0.94

ãĥĩãĤ£

0.75

ishment

0.72

 warheads

0.70

ishing

0.70

 spoiled

0.68

ishers

0.66

ishes

0.66

ãĥĺ

0.66

Activations Density 0.017%

words related to destruction or causing harm

instances of the word "destroy" and its variations

No Comments

No Known Activations