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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

rawdownloadcloneembedreportprint

-2.27

 Marketable

-2.06

racuse

-1.89

 GOODMAN

-1.82

channelAvailability

-1.81

 sqor

-1.71

ricular

-1.70

gdala

-1.69

GD

-1.68

fid

-1.68

POSITIVE LOGITS

oming

1.89

 flown

1.69

 disappearance

1.58

 Goth

1.57

 helicop

1.54

 disappear

1.53

 prototypes

1.52

 rend

1.51

fitted

1.50

 Rove

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.