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

2:0.09

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.09

9:0.11

10:0.09

11:0.07

Negative Logits

zsche

-1.98

saf

-1.82

gdala

-1.77

��

-1.76

 Leone

-1.65

aptic

-1.60

ッド

-1.58

Gad

-1.55

Pak

-1.52

 Blessing

-1.52

POSITIVE LOGITS

Reviewer

1.79

']

1.65

'),

1.65

 inaccur

1.53

 outp

1.53

 record

1.52

 ensued

1.51

enegger

1.48

 dispatcher

1.48

 campus

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.