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

Head Attr Weights

0:0.07

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.09

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

voy

-1.96

 hoard

-1.71

 conventions

-1.60

 domest

-1.55

 Schne

-1.53

 spec

-1.50

 Portug

-1.49

 acknowled

-1.49

 scarce

-1.49

 adul

-1.46

POSITIVE LOGITS

ackle

1.71

flag

1.69

Ak

1.67

termination

1.67

mist

1.64

icidal

1.63

then

1.61

ursive

1.60

united

1.56

ansson

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.