INDEX

Explanations

references to the NRA (National Rifle Association)

oai_token-act-pair · gpt-3.5-turbo

references to the NRA (National Rifle Association)

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hai

-0.73

é£

-0.72

lict

-0.72

hw

-0.68

 Archdemon

-0.68

Yi

-0.68

graded

-0.65

loe

-0.64

esley

-0.64

 Grail

-0.64

POSITIVE LOGITS

 patriarch

0.81

IGHTS

0.80

 firearms

0.75

 Firearms

0.74

UTH

0.74

IFIC

0.73

senal

0.73

 membership

0.73

istani

0.71

NRA

0.71

Activations Density 0.022%

references to the NRA (National Rifle Association)

references to the NRA (National Rifle Association)

No Comments

No Known Activations