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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.09

3:0.07

4:0.07

5:0.08

6:0.08

7:0.07

8:0.10

9:0.07

10:0.08

11:0.08

Negative Logits

 previews

-1.68

 Guests

-1.65

 Logged

-1.65

 keynote

-1.56

 attendees

-1.52

 voiced

-1.51

 particularly

-1.49

 onstage

-1.49

 credits

-1.48

...)

-1.48

POSITIVE LOGITS

Js

1.81

tera

1.75

lif

1.67

cius

1.60

wx

1.57

Connector

1.56

illac

1.53

Asia

1.53

Apps

1.52

 Median

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.