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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.09

3:0.08

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

Fib

-1.81

Lob

-1.80

 Antiqu

-1.67

 Punch

-1.67

 Sports

-1.65

 WiFi

-1.62

 Scar

-1.60

 Iris

-1.58

Zur

-1.57

 (−

-1.57

POSITIVE LOGITS

odge

1.97

achine

1.96

gaard

1.92

uga

1.89

oad

1.89

anka

1.88

visors

1.86

 retake

1.85

actionDate

1.83

rex

1.83

Activations Density 0.000%

No Known Activations

This feature has no known activations.