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

1:0.07

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.10

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 clich

-1.67

Reviewer

-1.55

UGH

-1.53

 Nile

-1.49

endor

-1.46

nos

-1.44

 Subtle

-1.43

":["

-1.42

 Gundam

-1.42

 glory

-1.41

POSITIVE LOGITS

phrine

1.74

 disposed

1.60

PAC

1.55

 bindings

1.54

 dumps

1.51

 exited

1.50

 exchanges

1.49

 broker

1.46

 steril

1.45

 deposited

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.