INDEX

Explanations

references to poetry and its cultural significance.

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

0:0.26

1:0.04

2:0.08

3:0.05

4:0.07

5:0.02

6:0.09

7:0.15

8:0.02

9:0.03

10:0.08

11:0.07

Negative Logits

 Gear

-3.71

 Kinect

-3.69

 Franchise

-3.50

Gear

-3.17

MLG

-3.11

 Shinra

-3.11

omaly

-3.11

 franch

-3.03

 Borderlands

-2.98

Xbox

-2.93

POSITIVE LOGITS

 poems

7.08

 poem

6.94

 poets

6.92

 poetry

6.43

 poet

6.23

 poetic

5.61

 lyric

4.71

 Twain

4.56

 Eliot

4.39

 verse

4.29

Activations Density 0.028%

references to poetry and its cultural significance.

No Comments

No Known Activations