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

3:0.08

4:0.09

5:0.09

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

��

-1.83

pse

-1.80

YPG

-1.80

 Flavoring

-1.72

aneers

-1.71

 Pesh

-1.69

Tex

-1.65

 Educ

-1.64

 traged

-1.64

icter

-1.64

POSITIVE LOGITS

erous

1.77

 median

1.67

 Bohem

1.66

typ

1.61

 cottage

1.59

cause

1.59

 gorge

1.54

 dwellings

1.50

forest

1.50

 typical

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.