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

0:0.07

1:0.05

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.09

10:0.09

11:0.07

Negative Logits

 visitation

-1.73

 Shutterstock

-1.50

 seizure

-1.48

 blackout

-1.48

Gaz

-1.47

 ensu

-1.46

 listener

-1.44

 Raspberry

-1.43

 exhib

-1.43

 Prohibition

-1.43

POSITIVE LOGITS

ngth

2.34

umenthal

2.06

llan

1.80

ignt

1.80

tein

1.79

inet

1.79

hene

1.73

isively

1.72

fab

1.72

cmd

1.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.