INDEX

Explanations

web addresses or URLs

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

2:0.07

3:0.04

4:0.06

5:0.03

6:0.07

7:0.17

8:0.06

9:0.05

10:0.27

11:0.08

Negative Logits

 helicop

-1.86

 UNCLASSIFIED

-1.86

 stationed

-1.81

enegger

-1.63

 calibr

-1.61

 inaug

-1.60

 ashore

-1.60

keeping

-1.55

JUST

-1.52

 cabinets

-1.49

POSITIVE LOGITS

��

2.30

lectic

1.67

asher

1.67

pmwiki

1.65

dimensional

1.63

Writing

1.62

bidden

1.61

genre

1.59

 Dungeons

1.55

MpServer

1.48

Activations Density 0.000%

web addresses or URLs

No Comments

No Known Activations