INDEX

Explanations

phrases related to service operations and government functions

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

0:0.07

1:0.21

2:0.10

3:0.06

4:0.03

5:0.03

6:0.09

7:0.09

8:0.02

9:0.05

10:0.15

11:0.04

Negative Logits

Reviewer

-2.57

np

-2.57

 override

-2.54

ahoo

-2.47

 Nikki

-2.45

uala

-2.43

nn

-2.41

 Pryor

-2.40

 overwrite

-2.39

 Schne

-2.39

POSITIVE LOGITS

 Cent

7.54

Cent

6.82

 cent

6.02

 CENT

4.72

cent

4.62

CENT

4.24

 Century

3.91

 Cald

3.80

icent

3.40

 Centre

3.39

Activations Density 0.007%

phrases related to service operations and government functions

No Comments

No Known Activations