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

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.09

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

 racket

-1.90

 signalling

-1.66

 grappling

-1.64

 defenses

-1.59

 defences

-1.59

pse

-1.55

 drafting

-1.54

 suprem

-1.52

 acknow

-1.49

 behav

-1.48

POSITIVE LOGITS

velength

2.04

spons

1.70

dose

1.69

ometown

1.68

zech

1.65

hoe

1.63

ugs

1.61

BuyableInstoreAndOnline

1.61

clinical

1.60

Ingredients

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.