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

Head Attr Weights

0:0.07

1:0.06

2:0.09

3:0.08

4:0.07

5:0.09

6:0.09

7:0.08

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

isition

-1.87

 reusable

-1.82

rogens

-1.79

eros

-1.74

gram

-1.73

pload

-1.68

ourcing

-1.67

rote

-1.66

 replaces

-1.64

hips

-1.62

POSITIVE LOGITS

natureconservancy

2.23

龍契士

2.10

interstitial

1.93

�

1.93

GMT

1.72

龍喚士

1.67

EStream

1.63

Hung

1.61

 Stalin

1.57

�

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.