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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.06

10:0.08

11:0.08

Negative Logits

UTC

-1.79

viz

-1.79

bryce

-1.72

Untitled

-1.59

ANGE

-1.58

ALE

-1.55

pse

-1.54

 referen

-1.52

Zup

-1.51

 ARTICLE

-1.50

POSITIVE LOGITS

depend

1.73

 antidepressants

1.72

rahim

1.70

helps

1.68

 fluids

1.60

nerg

1.57

ols

1.52

brainer

1.51

 deterrent

1.49

ridges

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.