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

0:0.09

1:0.05

2:0.10

3:0.12

4:0.07

5:0.05

6:0.05

7:0.04

8:0.10

9:0.08

10:0.09

11:0.10

Negative Logits

(?,

-1.54

 Transactions

-1.53

omorphic

-1.52

 recommends

-1.47

 Correct

-1.45

 proposes

-1.43

problem

-1.37

 Procedure

-1.37

 describes

-1.33

 Solitaire

-1.33

POSITIVE LOGITS

 cuff

1.90

��

1.58

EMS

1.48

 buckle

1.48

Tro

1.47

tones

1.44

>]

1.43

 later

1.43

%).

1.39

CLOSE

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.