INDEX

Explanations

No Explanations Found

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

0:0.08

1:0.07

2:0.10

3:0.07

4:0.10

5:0.06

6:0.07

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 newcom

-1.61

×

-1.52

 Pengu

-1.47

 veter

-1.46

 boutique

-1.45

 Unch

-1.45

 lifelong

-1.45

shop

-1.44

 Moroc

-1.43

 Intern

-1.42

POSITIVE LOGITS

finger

1.98

yip

1.88

govtrack

1.67

opus

1.64

perature

1.62

itiz

1.60

finding

1.60

bleacher

1.59

vernment

1.59

phony

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.