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

0:0.07

1:0.08

2:0.08

3:0.10

4:0.07

5:0.08

6:0.08

7:0.10

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

��

-1.96

 spoiler

-1.67

 sleeper

-1.62

 atroc

-1.58

 ours

-1.57

 squares

-1.55

 Tomorrow

-1.51

 Soviets

-1.51

achev

-1.51

 Jenner

-1.51

POSITIVE LOGITS

��極

1.94

══

1.86

ESA

1.84

ゴ

1.84

Support

1.83

1.82

HAM

1.79

coord

1.73

Dri

1.73

ptoms

1.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.