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

0:0.06

1:0.07

2:0.09

3:0.09

4:0.07

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

Nug

-2.13

 Marse

-1.82

Sources

-1.69

Hud

-1.61

 Hours

-1.61

Kut

-1.61

 Kling

-1.60

 Loud

-1.59

Dug

-1.58

 Museum

-1.56

POSITIVE LOGITS

omorphic

1.93

utics

1.79

ijk

1.75

 partName

1.74

 horizont

1.72

iate

1.70

oters

1.70

 actu

1.68

edom

1.67

artments

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.