INDEX

Explanations

words related to evil or negative characteristics

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "evil."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akeru

-0.78

dropping

-0.77

eding

-0.76

GN

-0.75

PsyNetMessage

-0.74

UNCH

-0.73

ribe

-0.73

kees

-0.73

amen

-0.72

aro

-0.72

POSITIVE LOGITS

 incarn

1.03

 deeds

0.94

 deed

0.90

nesses

0.89

 mastermind

0.87

 twin

0.83

 genius

0.81

 lord

0.77

 evil

0.77

NESS

0.77

Activations Density 0.028%

words related to evil or negative characteristics

references to the concept of "evil."

No Comments

No Known Activations