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

1:0.08

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.07

9:0.08

10:0.10

11:0.08

Negative Logits

 Breitbart

-1.60

-1.57

 Tablet

-1.51

nesday

-1.49

 Archive

-1.49

 Byte

-1.48

rase

-1.46

itbart

-1.46

 Sinclair

-1.46

encer

-1.44

POSITIVE LOGITS

 seiz

1.70

burgh

1.66

Sov

1.63

 behav

1.62

 veter

1.60

Reviewer

1.60

 fortun

1.59

 nodd

1.57

 hous

1.55

 Galile

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.