INDEX

Explanations

references to significant cultural or political events and their implications

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

0:0.03

1:0.02

2:0.13

3:0.20

4:0.09

5:0.05

6:0.03

7:0.05

8:0.08

9:0.10

10:0.08

11:0.09

Negative Logits

ascript

-1.81

ngth

-1.63

agra

-1.63

plet

-1.58

anwhile

-1.52

acebook

-1.49

jri

-1.49

mercial

-1.49

)."

-1.47

aditional

-1.47

POSITIVE LOGITS

 Review

1.28

 roundup

1.16

 Prompt

1.14

 Critics

1.13

 Preview

1.09

 Advocate

1.08

 Warranty

1.07

 horm

1.04

 Planes

1.04

IGN

1.04

Activations Density 0.078%

references to significant cultural or political events and their implications

No Comments

No Known Activations