INDEX

Explanations

words related to actions of undermining or discrediting

oai_token-act-pair · gpt-3.5-turbo

phrases related to attempts to weaken or sabotage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lov

-0.71

area

-0.67

ather

-0.66

andro

-0.65

Spoiler

-0.63

cise

-0.63

////////

-0.62

onna

-0.62

çĦ

-0.61

flo

-0.60

POSITIVE LOGITS

 havoc

0.83

 perceptions

0.76

 expectations

0.73

 undermin

0.73

 morale

0.72

 livelihood

0.70

 undermining

0.68

 attempts

0.67

ments

0.67

 deterrence

0.67

Activations Density 0.045%

words related to actions of undermining or discrediting

phrases related to attempts to weaken or sabotage

No Comments

No Known Activations