INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

2:0.08

3:0.06

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

angular

-1.88

oots

-1.75

idable

-1.73

atin

-1.67

next

-1.65

api

-1.64

cod

-1.62

otos

-1.62

inders

-1.61

own

-1.58

POSITIVE LOGITS

¶

1.69

 =================

1.67

 criticised

1.67

 Lange

1.61

quickShipAvailable

1.59

 omission

1.58

 nutshell

1.48

 defamation

1.46

 Anthrop

1.46

ⓘ

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.