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

0:0.08

1:0.08

2:0.07

3:0.07

4:0.08

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.09

Negative Logits

)=(

-2.39

riction

-1.89

Seg

-1.73

nered

-1.68

 Supplementary

-1.67

 flats

-1.66

 coincided

-1.66

 pressured

-1.66

 capped

-1.65

 vicinity

-1.65

POSITIVE LOGITS

 Osiris

2.16

2.01

 Isis

1.99

1.92

 mankind

1.88

 cous

1.86

awe

1.84

 idols

1.84

 weap

1.84

onom

1.84

Activations Density 0.000%

No Known Activations

This feature has no known activations.