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

3:0.09

4:0.10

5:0.07

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.07

Negative Logits

 retweet

-1.75

 Spotify

-1.60

 Macron

-1.57

 fruitful

-1.56

Discover

-1.45

 thanking

-1.43

 iTunes

-1.41

 revealing

-1.41

 Medium

-1.40

"],"

-1.40

POSITIVE LOGITS

rag

1.74

��

1.66

��

1.54

 Scand

1.53

gas

1.49

�

1.49

mare

1.48

angular

1.47

神

1.43

awa

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.