INDEX

Explanations

references to observations or perceptions regarding individuals or groups

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

0:0.01

1:0.01

2:0.07

3:0.07

4:0.12

5:0.02

6:0.05

7:0.42

8:0.03

9:0.03

10:0.05

11:0.05

Negative Logits

etta

-1.63

ichever

-1.46

urances

-1.46

seless

-1.45

ailed

-1.44

iability

-1.43

onsense

-1.43

este

-1.42

omial

-1.41

wald

-1.40

POSITIVE LOGITS

 theaters

1.43

 Drift

1.41

 Trader

1.38

 afar

1.36

 blink

1.33

 Exhibit

1.31

 Palo

1.30

 malls

1.29

izens

1.28

Yad

1.27

Activations Density 0.021%

references to observations or perceptions regarding individuals or groups

No Comments

No Known Activations