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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.07

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.09

9:0.07

10:0.09

11:0.08

Negative Logits

 waived

-1.90

 waivers

-1.88

dash

-1.72

 waiver

-1.71

catentry

-1.71

llah

-1.62

 thumbs

-1.58

osponsors

-1.57

 blocked

-1.54

 resignation

-1.48

POSITIVE LOGITS

 Dictionary

1.76

~~~~~~~~

1.75

 Indigo

1.69

OOL

1.66

��

1.64

Occ

1.64

 Elys

1.64

覚醒

1.63

 Basics

1.62

 inhab

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.