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

0:0.07

1:0.05

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.10

11:0.09

Negative Logits

 Exercise

-1.69

 Tennis

-1.67

 Activities

-1.61

 Sport

-1.59

 Extensions

-1.57

 Injury

-1.55

 Experience

-1.53

 Examiner

-1.51

 Classification

-1.50

 Races

-1.50

POSITIVE LOGITS

luaj

1.70

�

1.59

pret

1.53

1.49

═

1.48

�

1.46

rate

1.45

assuming

1.44

�

1.42

sburg

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.