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

1:0.06

2:0.10

3:0.08

4:0.07

5:0.08

6:0.07

7:0.09

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

 Rowe

-1.98

 debunk

-1.85

 reprinted

-1.74

 dashed

-1.70

 Belichick

-1.68

 Hawking

-1.67

 Hayden

-1.62

 reader

-1.61

 stall

-1.60

 Kemp

-1.58

POSITIVE LOGITS

*/(

2.07

puted

1.77

owered

1.75

 favour

1.73

Shape

1.72

doms

1.72

Reward

1.70

merce

1.70

omin

1.68

rica

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.