INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.08

1:0.07

2:0.07

3:0.09

4:0.10

5:0.09

6:0.09

7:0.07

8:0.09

9:0.07

10:0.06

11:0.08

Negative Logits

etheless

-2.43

@#&

-2.16

anguages

-2.13

ongevity

-2.11

ength

-2.10

aples

-2.09

enos

-2.07

sylv

-2.04

berra

-2.00

ITH

-1.98

POSITIVE LOGITS

 Maul

2.25

 Thrust

2.07

Hunt

2.03

 Blaster

2.03

Mask

1.94

 Plate

1.93

 Strike

1.91

 Pill

1.88

Mk

1.87

 Pump

1.87

Activations Density 0.000%

No Known Activations

This feature has no known activations.