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

0:0.08

1:0.06

2:0.09

3:0.09

4:0.07

5:0.07

6:0.09

7:0.07

8:0.08

9:0.06

10:0.10

11:0.08

Negative Logits

igrate

-1.79

metic

-1.67

ulative

-1.57

metics

-1.51

Merit

-1.49

 visibility

-1.49

irtual

-1.47

Reviewer

-1.44

umerable

-1.43

 transactions

-1.40

POSITIVE LOGITS

isin

1.65

ollah

1.57

______

1.54

IER

1.52

clinton

1.49

iden

1.45

天

1.45

rador

1.44

itol

1.42

INTON

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.