INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

anus

-3.13

Aad

-2.90

 summers

-2.75

ixon

-2.75

 winters

-2.73

iston

-2.63

 guesses

-2.54

 nests

-2.48

ettings

-2.43

birds

-2.42

POSITIVE LOGITS

apesh

2.61

 transformative

2.56

scene

2.56

+#

2.52

#$

2.52

=#

2.52

 Catalyst

2.48

 Kash

2.46

 Exhibit

2.45

 Defendants

2.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.