INDEX

Explanations

terms related to legal or law enforcement actions

oai_token-act-pair · gpt-3.5-turbo

references to legal and law enforcement entities

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

tein

-0.65

 lives

-0.64

Py

-0.60

lander

-0.60

 Purg

-0.58

gone

-0.57

lost

-0.56

CHAT

-0.56

:=

-0.56

surv

-0.55

POSITIVE LOGITS

DERR

0.78

 censor

0.74

¶ħ

0.73

istrate

0.71

 inspectors

0.71

 probing

0.70

 Archdemon

0.68

 authorities

0.68

 magistrate

0.66

 undet

0.66

Activations Density 0.450%

terms related to legal or law enforcement actions

references to legal and law enforcement entities

No Comments

No Known Activations