INDEX

Explanations

punctuation marks or sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.25

2:0.04

3:0.03

4:0.04

5:0.03

6:0.20

7:0.08

8:0.03

9:0.05

10:0.04

11:0.06

Negative Logits

WM

-1.63

覚醒

-1.62

HMS

-1.52

 STATS

-1.47

IND

-1.45

ADA

-1.45

в

-1.44

TAM

-1.43

ATK

-1.39

MAP

-1.38

POSITIVE LOGITS

 sucked

1.67

avoid

1.48

gery

1.40

iscons

1.40

 Grassley

1.40

 forgiven

1.38

gered

1.37

comed

1.35

nel

1.35

ifully

1.33

Activations Density 0.000%

punctuation marks or sentence endings

No Comments

No Known Activations