INDEX

Explanations

references to different agencies or organizations

oai_token-act-pair · gpt-3.5-turbo

references to various agencies

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

erous

-0.76

sticks

-0.75

eness

-0.74

bedroom

-0.73

castle

-0.72

steen

-0.71

etting

-0.71

neapolis

-0.70

aunder

-0.69

lasses

-0.69

POSITIVE LOGITS

 Agency

0.88

UTH

0.81

ENCY

0.79

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.73

 Administrator

0.72

ption

0.71

 Consortium

0.71

 Coord

0.70

uthor

0.69

 Employees

0.69

Activations Density 0.019%

references to different agencies or organizations

references to various agencies

No Comments

No Known Activations