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

1:0.04

2:0.10

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

atre

-1.90

WWF

-1.78

 wrestling

-1.72

emale

-1.60

calling

-1.57

 Wrestling

-1.54

 redes

-1.53

opolis

-1.48

 Prompt

-1.47

 Wanted

-1.42

POSITIVE LOGITS

 layers

1.75

bun

1.71

 twists

1.66

 fung

1.65

 fruits

1.65

 pores

1.60

fruit

1.58

 sunlight

1.58

 frost

1.58

 curves

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.