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

1:0.08

2:0.09

3:0.09

4:0.08

5:0.06

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

zhou

-1.98

)</

-1.89

endez

-1.72

aug

-1.68

 Regarding

-1.65

)",

-1.64

sburg

-1.64

++)

-1.61

 Recall

-1.57

anu

-1.57

POSITIVE LOGITS

gravity

1.63

circle

1.55

 notation

1.55

 monopoly

1.44

drawn

1.43

 society

1.41

 curs

1.37

 laureate

1.36

phies

1.35

 dollar

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.