INDEX

Explanations

references to social issues and demographics

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

New Auto-Interp

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

0:0.03

1:0.02

2:0.10

3:0.06

4:0.07

5:0.11

6:0.05

7:0.03

8:0.03

9:0.11

10:0.16

11:0.17

Negative Logits

borgh

-1.17

,,,,

-1.14

rolet

-1.08

 Fenrir

-1.04

=-=-=-=-=-=-=-=-

-1.02

itech

-1.00

??

-0.99

dylib

-0.98

lahoma

-0.97

ja

-0.97

POSITIVE LOGITS

 penetrate

1.18

 dens

1.13

 complicate

1.11

 beware

1.08

 visualize

1.08

 penetrated

1.07

 inaccur

1.02

 converge

1.02

 frequently

1.01

 deepen

1.00

Activations Density 0.401%

references to social issues and demographics

No Comments

No Known Activations