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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

ubes

-1.86

ngth

-1.79

plings

-1.75

ppers

-1.74

pees

-1.73

 Drops

-1.73

 Spit

-1.73

llular

-1.69

 teasp

-1.68

plet

-1.68

POSITIVE LOGITS

ICO

1.97

Independent

1.95

GREEN

1.64

ERA

1.64

ISION

1.59

Dialog

1.59

ORTS

1.58

 dispute

1.57

DEP

1.56

LOS

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.