INDEX

Explanations

rhetorical questions

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

3:0.07

4:0.06

5:0.04

6:0.04

7:0.27

8:0.04

9:0.05

10:0.04

11:0.24

Negative Logits

 Kling

-2.07

Jem

-1.83

Nex

-1.80

 Malf

-1.76

Crew

-1.74

 announ

-1.72

 Franch

-1.71

 Voyager

-1.69

Vec

-1.66

 restrooms

-1.65

POSITIVE LOGITS

 empowering

1.85

 advocating

1.80

onga

1.75

ensity

1.73

 Giving

1.72

 punishing

1.68

yip

1.65

 granting

1.62

 recommending

1.60

 indict

1.60

Activations Density 0.001%

rhetorical questions

No Comments

No Known Activations