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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Bugs

-1.81

SAP

-1.60

fug

-1.59

-1.56

 amen

-1.55

GMT

-1.54

 motorists

-1.54

 hump

-1.53

ahi

-1.51

 allerg

-1.49

POSITIVE LOGITS

urations

2.19

igated

1.81

rafted

1.72

ivan

1.72

urated

1.71

ificant

1.68

ivari

1.65

iaries

1.65

 tidal

1.64

arnaev

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.