INDEX

Explanations

phrases that provide a summary or essential points of a discussion

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

Head Attr Weights

0:0.02

1:0.03

2:0.10

3:0.07

4:0.10

5:0.02

6:0.06

7:0.39

8:0.03

9:0.03

10:0.04

11:0.04

Negative Logits

ubs

-1.80

osponsors

-1.61

gged

-1.53

river

-1.50

龍

-1.49

frog

-1.41

umb

-1.40

wait

-1.37

odan

-1.37

iger

-1.36

POSITIVE LOGITS

 gist

1.81

AST

1.73

Analysis

1.55

 satire

1.43

ans

1.42

Discuss

1.39

 Statement

1.38

message

1.37

 boils

1.37

\-

1.35

Activations Density 0.001%

phrases that provide a summary or essential points of a discussion

No Known Activations