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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.09

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

ocratic

-1.83

rament

-1.78

 bidder

-1.78

rious

-1.73

ocracy

-1.71

mingham

-1.64

rul

-1.63

edom

-1.58

 royalty

-1.54

 dressing

-1.50

POSITIVE LOGITS

UGC

1.76

EV

1.66

NRS

1.64

Scan

1.59

 Surve

1.55

bc

1.53

map

1.52

 scan

1.50

 surveys

1.49

Maps

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.