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

2:0.07

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

SPONSORED

-1.92

 Wolves

-1.61

 hotel

-1.61

 Kaiser

-1.61

 Sherman

-1.58

aughs

-1.56

 poor

-1.56

 Blitz

-1.54

 Mobil

-1.54

�

-1.53

POSITIVE LOGITS

®

2.30

 confir

2.00

rules

1.73

igure

1.72

module

1.68

 largeDownload

1.67

translation

1.66

hare

1.66

arist

1.66

yo

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.