INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.07

5:0.07

6:0.09

7:0.08

8:0.07

9:0.09

10:0.07

11:0.09

Negative Logits

venue

-3.13

Reviewer

-2.75

 navigating

-2.67

 gigs

-2.61

 Remix

-2.60

 pedals

-2.59

 Gadget

-2.57

 Bounce

-2.56

Tube

-2.56

 Catalyst

-2.53

POSITIVE LOGITS

 Brach

2.72

apons

2.72

opath

2.64

 Cubs

2.60

 ILCS

2.55

 Sonia

2.55

 rested

2.54

ilipp

2.53

zech

2.46

hol

2.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.