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

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

oscope

-1.84

 Shutterstock

-1.82

igible

-1.76

Eye

-1.60

XT

-1.59

imeo

-1.55

ト

-1.47

osc

-1.46

 Suit

-1.45

ITV

-1.43

POSITIVE LOGITS

ateurs

1.64

spection

1.57

 establishment

1.57

 generations

1.55

 drafting

1.44

 reproduction

1.42

 Colonel

1.41

DERR

1.41

 Lieutenant

1.38

dayName

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.