INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.07

2:0.07

3:0.08

4:0.07

5:0.07

6:0.08

7:0.09

8:0.08

9:0.09

10:0.09

11:0.07

Negative Logits

 Meng

-3.19

 Deng

-2.75

 Zhou

-2.61

icator

-2.59

Ts

-2.54

Taj

-2.49

 Trend

-2.48

Lub

-2.38

icators

-2.33

 deepening

-2.32

POSITIVE LOGITS

mingham

3.72

letcher

3.09

fox

2.96

 Hert

2.74

 felon

2.72

 Lawyers

2.66

gamer

2.66

essions

2.65

mpeg

2.65

orney

2.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.