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

1:0.09

2:0.07

3:0.08

4:0.08

5:0.07

6:0.07

7:0.10

8:0.08

9:0.06

10:0.08

11:0.09

Negative Logits

——

-2.12

performance

-1.67

 herself

-1.60

++++

-1.52

ッ

-1.49

 grounds

-1.48

————

-1.48

?」

-1.45

 disadvant

-1.45

 hike

-1.44

POSITIVE LOGITS

2.36

ixtape

1.71

akespe

1.68

hesive

1.67

nesota

1.65

ournals

1.61

 archived

1.61

aden

1.61

gex

1.61

odic

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.