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

0:0.09

1:0.11

2:0.08

3:0.08

4:0.07

5:0.09

6:0.07

7:0.07

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

 Tone

-1.87

 Outlook

-1.77

 Cancel

-1.71

...)

-1.67

umn

-1.61

notice

-1.60

 Rober

-1.57

 Summit

-1.52

 Round

-1.51

ete

-1.50

POSITIVE LOGITS

fman

1.69

baugh

1.67

pter

1.66

aptic

1.62

minist

1.61

ctive

1.58

oaded

1.54

 coercion

1.53

erker

1.52

 robbers

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.