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

0:0.07

1:0.08

2:0.09

3:0.08

4:0.09

5:0.07

6:0.08

7:0.07

8:0.06

9:0.10

10:0.08

11:0.07

Negative Logits

table

-1.55

ixt

-1.53

ages

-1.51

rend

-1.43

 applicable

-1.42

EStreamFrame

-1.42

EStream

-1.40

aque

-1.37

 rounding

-1.33

bender

-1.32

POSITIVE LOGITS

ּ

1.75

CCC

1.68

cean

1.61

ukemia

1.55

Reilly

1.50

enegger

1.46

ONSORED

1.44

WB

1.42

ledged

1.41

kefeller

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.