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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.07

8:0.08

9:0.09

10:0.07

11:0.09

Negative Logits

 stranded

-1.76

�

-1.67

 hatched

-1.60

�

-1.60

 Khan

-1.58

 rounding

-1.57

��

-1.54

 PowerPoint

-1.52

 unearthed

-1.51

——

-1.51

POSITIVE LOGITS

ategory

1.86

obbies

1.82

 independ

1.63

Same

1.62

modules

1.58

terms

1.51

ordable

1.48

 girlfriends

1.45

 Hosp

1.45

iency

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.