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

0:0.09

1:0.05

2:0.06

3:0.08

4:0.08

5:0.09

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

imensional

-2.00

blogs

-1.96

 airing

-1.75

fest

-1.66

ombs

-1.57

 Defenders

-1.56

vable

-1.55

utterstock

-1.54

inki

-1.49

 podcast

-1.45

POSITIVE LOGITS

 rods

1.82

stroke

1.68

��

1.63

 Draco

1.63

borgh

1.62

 whisk

1.59

 Aram

1.56

 motorcycles

1.55

 Gujar

1.54

animate

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.