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

1:0.06

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

Witness

-1.69

Deploy

-1.69

hon

-1.65

VID

-1.63

Split

-1.61

Inv

-1.60

Interview

-1.58

ilon

-1.57

Marie

-1.53

Philipp

-1.53

POSITIVE LOGITS

 basics

1.72

 intersections

1.67

 streets

1.63

 Mondays

1.59

ageddon

1.57

nces

1.55

 Vern

1.54

 bustling

1.53

avascript

1.51

 Sundays

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.