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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.10

6:0.07

7:0.08

8:0.08

9:0.07

10:0.06

11:0.08

Negative Logits

bery

-1.80

ularity

-1.77

-)

-1.70

rium

-1.68

+)

-1.68

?)

-1.61

owitz

-1.59

?),

-1.58

?)

-1.58

 theorem

-1.55

POSITIVE LOGITS

ombat

1.97

 withd

1.74

Hop

1.59

�

1.56

1.55

 angrily

1.53

 acutely

1.50

�醒

1.46

 frantic

1.44

 calmly

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.