INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.07

2:0.07

3:0.08

4:0.09

5:0.08

6:0.09

7:0.08

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

*/(

-2.90

 freed

-2.72

 emancipation

-2.69

iership

-2.60

者

-2.60

 attrition

-2.59

 entitle

-2.55

 abolish

-2.50

 abolished

-2.49

EStream

-2.42

POSITIVE LOGITS

Rus

2.98

Pict

2.91

rils

2.80

Technical

2.80

Radio

2.74

Pa

2.74

Rub

2.73

■

2.67

Mat

2.64

Pont

2.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.