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

1:0.07

2:0.07

3:0.09

4:0.07

5:0.09

6:0.08

7:0.10

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

atorium

-1.84

giene

-1.82

 Pigs

-1.69

 Canaver

-1.67

 livest

-1.66

gars

-1.60

ordon

-1.59

raviolet

-1.58

pherd

-1.57

apo

-1.57

POSITIVE LOGITS

 oppos

1.75

 digits

1.75

 downt

1.59

 civic

1.58

ymm

1.55

 allegiance

1.53

 extension

1.50

 dependence

1.50

 stereotype

1.49

 fundamentals

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.