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

0:0.07

1:0.07

2:0.10

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

chart

-1.67

ipper

-1.67

RFC

-1.65

cli

-1.64

gem

-1.64

Record

-1.63

SON

-1.62

ramer

-1.62

ote

-1.62

POSITIVE LOGITS

 Bulgar

1.78

 Yanuk

1.75

 Siberian

1.72

 anus

1.64

 Hindus

1.61

Kaf

1.59

�

1.59

Ek

1.56

 skirt

1.51

 Bolshe

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.