INDEX

Explanations

the concept of similarity or equivalence

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

0:0.08

1:0.07

2:0.07

3:0.09

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

ARCH

-2.77

WARE

-2.62

Oo

-2.58

aneous

-2.55

�

-2.52

Tut

-2.51

AFB

-2.51

istries

-2.47

roe

-2.46

obar

-2.46

POSITIVE LOGITS

 culturally

2.52

skilled

2.44

Frames

2.37

plays

2.30

CLS

2.29

 economically

2.25

 socially

2.25

 brightest

2.22

ollywood

2.22

efficient

2.18

Activations Density 0.000%

the concept of similarity or equivalence

No Comments

No Known Activations