INDEX

Explanations

references to political figures and their actions in the context of elections

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

0:0.04

1:0.01

2:0.05

3:0.10

4:0.04

5:0.10

6:0.02

7:0.02

8:0.05

9:0.14

10:0.31

11:0.07

Negative Logits

 Palest

-1.31

[&

-1.27

 CLSID

-1.25

 Atari

-1.24

 allele

-1.23

 downstream

-1.23

 Shib

-1.21

 membr

-1.20

Cth

-1.19

 upstream

-1.18

POSITIVE LOGITS

president

1.70

 presidency

1.60

 presidential

1.57

 Leadership

1.56

ablishment

1.55

 aides

1.51

 Presidency

1.51

 Donald

1.50

 Presidential

1.50

realDonaldTrump

1.49

Activations Density 1.281%

references to political figures and their actions in the context of elections

No Comments

No Known Activations