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

0:0.08

1:0.07

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

iverse

-1.84

rity

-1.61

 darn

-1.61

 faithful

-1.57

!",

-1.57

ngth

-1.55

!.

-1.54

.",

-1.52

 misc

-1.52

 loyal

-1.51

POSITIVE LOGITS

 Atkins

1.69

 Weston

1.68

 Morse

1.66

 Nielsen

1.62

Morgan

1.57

 Shark

1.57

 Schne

1.56

�

1.56

stadt

1.55

 Quake

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.