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

0:0.06

1:0.11

2:0.07

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 continu

-1.54

 atoms

-1.50

 future

-1.47

 aborted

-1.45

 degradation

-1.43

utonium

-1.41

 vein

-1.41

 status

-1.40

 tert

-1.39

 sterling

-1.38

POSITIVE LOGITS

reb

1.94

jug

1.75

osate

1.67

[&

1.67

mpire

1.65

skirts

1.63

iar

1.61

torn

1.61

gee

1.58

icion

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.