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

0:0.07

1:0.06

2:0.08

3:0.07

4:0.09

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Boolean

-1.78

 slang

-1.75

ⓘ

-1.70

viation

-1.65

 shorthand

-1.61

 pronunciation

-1.60

 Runes

-1.59

 filtered

-1.53

 Goodbye

-1.51

 passwords

-1.50

POSITIVE LOGITS

HCR

1.97

 Lumpur

1.88

覚醒

1.69

 senate

1.61

 warr

1.60

anyahu

1.59

Dispatch

1.59

 sponsors

1.58

ACP

1.56

arag

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.