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

0:0.10

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

uries

-2.10

 Flavoring

-1.93

 Accounts

-1.87

 presses

-1.84

 Gamer

-1.77

���

-1.75

 Inspect

-1.74

 Dealer

-1.69

ths

-1.68

 Press

-1.68

POSITIVE LOGITS

rolet

1.55

ahime

1.51

 turnaround

1.49

 challeng

1.48

 smugg

1.47

 motivating

1.45

 staging

1.43

cedes

1.40

bod

1.40

─

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.