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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

legraph

-1.84

 Architects

-1.80

ichick

-1.69

wark

-1.64

 Schwarz

-1.63

efficient

-1.60

 Rahman

-1.59

lihood

-1.59

think

-1.57

ammers

-1.57

POSITIVE LOGITS

iro

2.02

 nude

1.97

 birthday

1.87

INO

1.84

osexual

1.79

 origins

1.75

 juven

1.75

ogenic

1.75

 birthplace

1.70

 bachelor

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.