INDEX

Explanations

references to political figures and their actions or statements

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

0:0.01

1:0.01

2:0.47

3:0.10

4:0.07

5:0.04

6:0.02

7:0.02

8:0.05

9:0.05

10:0.05

11:0.04

Negative Logits

orgetown

-1.78

 confir

-1.70

ゴン

-1.66

 veter

-1.56

utterstock

-1.51

ienne

-1.50

版

-1.42

LU

-1.41

 emph

-1.41

obin

-1.39

POSITIVE LOGITS

shall

1.63

will

1.58

 discriminated

1.58

should

1.49

 attackers

1.48

 Blumenthal

1.46

 Pose

1.39

would

1.38

might

1.36

asking

1.36

Activations Density 0.395%

references to political figures and their actions or statements

No Comments

No Known Activations