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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.06

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Tatt

-1.86

 Joined

-1.67

��

-1.66

Dra

-1.63

 Legislation

-1.60

 Dwarf

-1.59

 Malk

-1.58

 Spending

-1.55

 Scot

-1.55

 Philos

-1.53

POSITIVE LOGITS

pload

2.10

ague

2.01

hots

1.78

 await

1.76

apons

1.67

gor

1.67

cano

1.63

upid

1.62

ample

1.62

azel

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.