INDEX

Explanations

phrases and elements that suggest classification or categorization

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

3:0.04

4:0.08

5:0.02

6:0.16

7:0.36

8:0.03

9:0.03

10:0.06

11:0.07

Negative Logits

ebook

-1.86

-1.64

ounters

-1.61

シャ

-1.50

redits

-1.41

olphin

-1.40

DERR

-1.38

-1.35

 Cosponsors

-1.35

oled

-1.33

POSITIVE LOGITS

 pree

1.51

 collagen

1.39

CoC

1.39

 cohesive

1.36

 predis

1.35

 fabric

1.35

 pigment

1.34

 uranium

1.34

 subdivision

1.33

��

1.32

Activations Density 0.009%

phrases and elements that suggest classification or categorization

No Comments

No Known Activations