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

0:0.07

1:0.08

2:0.07

3:0.08

4:0.08

5:0.09

6:0.09

7:0.09

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

 Instit

-1.85

 Sack

-1.79

Obj

-1.78

 Abstract

-1.77

Cap

-1.71

 Agric

-1.69

 Produ

-1.68

Ecc

-1.67

 Brewing

-1.66

 Foster

-1.66

POSITIVE LOGITS

accompan

2.41

otos

2.08

skirts

2.06

oaded

1.94

perm

1.90

cens

1.83

loaded

1.79

ortment

1.78

esses

1.78

rarily

1.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.