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

1:0.10

2:0.08

3:0.08

4:0.07

5:0.07

6:0.05

7:0.07

8:0.10

9:0.07

10:0.08

11:0.08

Negative Logits

paces

-1.90

actionDate

-1.85

anan

-1.84

yll

-1.80

 semester

-1.67

paced

-1.65

meal

-1.62

ainers

-1.60

cise

-1.59

Topics

-1.59

POSITIVE LOGITS

��

1.71

1.61

zona

1.55

�

1.54

�

1.54

 Roku

1.53

atched

1.53

 Undead

1.52

cific

1.52

 Corvette

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.