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

2:0.08

3:0.09

4:0.06

5:0.08

6:0.09

7:0.09

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Exec

-1.97

 Applicant

-1.92

 Execution

-1.76

 ______

-1.75

 Edit

-1.71

 Continued

-1.67

 Specific

-1.65

Exec

-1.65

 Correct

-1.63

 Page

-1.62

POSITIVE LOGITS

alore

1.82

icion

1.81

 domest

1.75

ibaba

1.74

 craving

1.73

 subsid

1.73

 wholesale

1.73

staking

1.70

akery

1.69

 painstaking

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.