INDEX

Explanations

references to specific individuals or groups in a narrative context

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

1:0.02

2:0.10

3:0.06

4:0.22

5:0.03

6:0.05

7:0.26

8:0.04

9:0.04

10:0.06

11:0.05

Negative Logits

版

-1.86

owned

-1.56

UNCH

-1.52

umbai

-1.52

 FANTASY

-1.52

dates

-1.50

�

-1.47

gmail

-1.46

noon

-1.46

SHIP

-1.44

POSITIVE LOGITS

 senseless

1.63

 boredom

1.55

 hardness

1.55

 brute

1.51

 cynicism

1.45

 enemy

1.43

 ruthless

1.42

 landslide

1.40

 stereotypes

1.37

 terrorists

1.37

Activations Density 0.001%

references to specific individuals or groups in a narrative context

No Comments

No Known Activations