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

0:0.09

1:0.06

2:0.08

3:0.09

4:0.07

5:0.08

6:0.08

7:0.06

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 Convers

-1.64

uctions

-1.63

 detox

-1.60

aundering

-1.60

 exchanges

-1.59

 confisc

-1.54

ositories

-1.49

 implants

-1.49

 derailed

-1.47

 Letters

-1.47

POSITIVE LOGITS

Reviewer

1.67

Attributes

1.65

Tree

1.62

stretched

1.59

VG

1.59

ilion

1.59

plot

1.58

phe

1.55

Oracle

1.55

 DRAGON

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.