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

0:0.06

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

CLAIM

-1.90

 Survival

-1.68

 MUST

-1.67

☆

-1.63

��

-1.63

CLASS

-1.59

javascript

-1.59

----------

-1.59

amic

-1.56

 Fail

-1.56

POSITIVE LOGITS

 Rover

1.88

 Genie

1.84

dfx

1.69

 Bern

1.68

 ether

1.66

 Guan

1.62

 Collider

1.62

 whisk

1.58

 River

1.58

 Comput

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.