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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.09

3:0.07

4:0.07

5:0.08

6:0.10

7:0.10

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

OTA

-1.86

externalActionCode

-1.78

 CONTR

-1.74

 EDITION

-1.74

 Situation

-1.70

IRD

-1.69

��極

-1.68

��

-1.67

ILLE

-1.67

 Moral

-1.67

POSITIVE LOGITS

mercial

2.23

netflix

2.13

ulence

1.97

ache

1.84

rine

1.84

uesday

1.83

 respectively

1.81

 tast

1.79

enegger

1.77

watching

1.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.