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

0:0.06

1:0.11

2:0.10

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

 Irwin

-1.66

alls

-1.60

Nug

-1.54

 Accessed

-1.54

 Interior

-1.53

 Chim

-1.53

 Rober

-1.48

lishing

-1.46

 Kemp

-1.46

 inherit

-1.45

POSITIVE LOGITS

 learners

1.74

isite

1.68

heid

1.65

 veter

1.65

 competence

1.61

halla

1.59

 hemisphere

1.58

geries

1.57

 lessons

1.56

 behavi

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.