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

0:0.10

1:0.06

2:0.09

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

speech

-1.67

unci

-1.66

Monster

-1.64

ERROR

-1.61

tor

-1.60

lit

-1.59

drops

-1.59

Delete

-1.57

ipient

-1.57

rar

-1.55

POSITIVE LOGITS

 Balt

1.85

heny

1.78

 Continuous

1.70

 Pyth

1.67

heast

1.66

 Cycling

1.62

Balt

1.62

 oats

1.60

[&

1.58

 Huntington

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.