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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

aiden

-1.72

adle

-1.64

iphate

-1.64

izard

-1.62

antis

-1.61

 Inquisition

-1.60

 Beir

-1.58

 Benghazi

-1.53

 Isis

-1.51

 Abbas

-1.48

POSITIVE LOGITS

paced

1.65

rawdownloadcloneembedreportprint

1.60

regor

1.59

 quickest

1.55

ertodd

1.54

igslist

1.51

uitive

1.48

por

1.47

itially

1.44

glomer

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.