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

1:0.06

2:0.08

3:0.08

4:0.11

5:0.07

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

Thompson

-1.63

 beetles

-1.61

 myster

-1.58

 Stevenson

-1.54

auder

-1.53

 Davidson

-1.52

 methodological

-1.51

 horm

-1.49

Fra

-1.47

 spectator

-1.46

POSITIVE LOGITS

 Assass

1.98

thood

1.87

1.85

itures

1.78

 referenced

1.70

=>

1.67

ignt

1.66

zbollah

1.65

translation

1.59

umbnail

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.