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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

OTA

-1.69

monkey

-1.66

 negro

-1.65

quit

-1.63

Equ

-1.63

git

-1.62

tc

-1.56

Intern

-1.54

Gamer

-1.53

pac

-1.52

POSITIVE LOGITS

ailability

2.58

��

2.08

ersive

1.92

srf

1.79

vity

1.77

idth

1.77

enegger

1.73

uesday

1.72

oppable

1.72

 lawy

1.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.