INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

0:0.08

1:0.08

2:0.09

3:0.07

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

ADA

-3.77

committee

-3.22

Fair

-3.09

 subcommittee

-2.91

ixel

-2.90

FF

-2.89

df

-2.82

CB

-2.81

DEF

-2.81

intel

-2.79

POSITIVE LOGITS

 despair

2.59

 melanch

2.59

 cursing

2.54

 Lith

2.54

 ravaged

2.52

yrus

2.51

 dying

2.50

 gripped

2.49

 slaughter

2.48

 stricken

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.