INDEX

Explanations

references to women and women-related topics

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

2:0.04

3:0.04

4:0.05

5:0.02

6:0.38

7:0.14

8:0.03

9:0.03

10:0.12

11:0.05

Negative Logits

cules

-1.51

icles

-1.42

agonist

-1.40

hitting

-1.38

 indebted

-1.36

icycle

-1.35

coat

-1.34

kick

-1.34

xit

-1.31

kay

-1.30

POSITIVE LOGITS

ItemTracker

1.73

ーテ

1.69

CLASSIFIED

1.50

ゴン

1.46

abase

1.45

 newcom

1.42

 agre

1.41

�醒

1.36

��

1.36

 sidx

1.35

Activations Density 0.003%

references to women and women-related topics

No Comments

No Known Activations