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

0:0.07

1:0.06

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 spec

-1.92

 resear

-1.90

 rods

-1.83

 paintings

-1.77

 brushes

-1.76

 paints

-1.73

 bart

-1.72

 torches

-1.71

 distribut

-1.71

 discounts

-1.69

POSITIVE LOGITS

BALL

1.90

facing

1.87

uberty

1.79

emies

1.77

cknow

1.68

achus

1.68

Warning

1.67

deen

1.65

onomous

1.65

asis

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.