INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.07

3:0.08

4:0.09

5:0.09

6:0.10

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

bringer

-2.66

 Polic

-2.64

anyahu

-2.60

oxide

-2.59

 undone

-2.53

 violently

-2.46

ł

-2.45

Pg

-2.43

achine

-2.41

ihadi

-2.40

POSITIVE LOGITS

 agre

2.82

Uni

2.73

 Hort

2.67

riad

2.55

 Twin

2.54

 DIRECT

2.51

sat

2.51

eger

2.49

 trustee

2.48

NAS

2.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.