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

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.10

7:0.08

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

arching

-1.80

ittle

-1.77

 threaded

-1.61

 appreciated

-1.57

 throughput

-1.54

resso

-1.51

 resilience

-1.51

 enthus

-1.50

 focuses

-1.48

 tuned

-1.47

POSITIVE LOGITS

idas

1.93

kai

1.73

][

1.68

ilk

1.62

 DISTRICT

1.56

�

1.55

アル

1.52

ーティ

1.50

$$$$

1.50

];

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.