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

0:0.07

1:0.08

2:0.07

3:0.09

4:0.07

5:0.07

6:0.08

7:0.10

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

IRC

-2.67

hops

-2.33

enhagen

-2.17

 Anon

-2.17

 Answers

-2.11

Wan

-2.08

 Begins

-2.06

?:

-2.04

MIT

-2.03

>(

-2.01

POSITIVE LOGITS

 luxurious

2.17

 plun

2.16

 fountain

2.11

 trave

2.08

 visc

2.08

 liqu

2.07

 gasoline

2.04

 digestion

2.02

 cubic

2.00

 jewelry

1.99

Activations Density 0.000%

No Known Activations

This feature has no known activations.