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

3:0.07

4:0.10

5:0.07

6:0.06

7:0.08

8:0.10

9:0.07

10:0.08

11:0.09

Negative Logits

Avg

-1.65

 Quantity

-1.58

龍�

-1.57

strate

-1.57

ogens

-1.52

 Calculator

-1.51

 Abilities

-1.50

ainment

-1.49

raints

-1.47

itives

-1.46

POSITIVE LOGITS

ker

1.74

vernment

1.69

borough

1.65

ONT

1.57

jam

1.52

forth

1.50

****************

1.49

colour

1.43

flower

1.40

helm

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.