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

2:0.07

3:0.07

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

etheless

-1.80

atown

-1.69

daq

-1.67

namese

-1.63

vre

-1.63

agascar

-1.63

anmar

-1.57

ebin

-1.56

jab

-1.54

yip

-1.54

POSITIVE LOGITS

 concent

1.58

Newsletter

1.56

 furn

1.54

 preserves

1.51

 superv

1.50

 cooper

1.46

 supervised

1.41

othe

1.36

 chrom

1.36

 interpre

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.