INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

 arrang

-2.80

 ende

-2.77

 patri

-2.75

 contempl

-2.67

 eleph

-2.63

 peac

-2.62

 negotiators

-2.61

 barg

-2.54

 negotiator

-2.53

 arsen

-2.51

POSITIVE LOGITS

 Citation

3.15

 Ratings

2.99

 Score

2.99

 Dupl

2.91

 Tick

2.87

 Bite

2.83

 Hits

2.83

 Fatal

2.80

 Carnage

2.79

 Strikes

2.76

Activations Density 0.000%

No Known Activations

This feature has no known activations.