INDEX

Explanations

discussions about political accountability and social issues

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

0:0.02

1:0.01

2:0.07

3:0.36

4:0.06

5:0.04

6:0.02

7:0.02

8:0.05

9:0.09

10:0.13

11:0.07

Negative Logits

 yours

-1.61

 VICE

-1.47

schild

-1.37

 bestselling

-1.31

ategor

-1.31

,'"

-1.31

 namesake

-1.31

aye

-1.31

 POLITICO

-1.29

NPR

-1.29

POSITIVE LOGITS

NetMessage

2.07

��

1.96

wcs

1.82

taboola

1.72

 "…

1.66

 "...

1.62

 outwe

1.60

ysc

1.57

�

1.56

 interfered

1.50

Activations Density 0.513%

discussions about political accountability and social issues

No Comments

No Known Activations