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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.09

8:0.08

9:0.07

10:0.06

11:0.08

Negative Logits

 ethical

-1.98

 accommodations

-1.90

 methodological

-1.83

ethical

-1.78

 affordability

-1.75

Aid

-1.75

Ori

-1.72

 accommodation

-1.72

ocrin

-1.66

ITCH

-1.63

POSITIVE LOGITS

inth

2.06

tein

1.82

��

1.77

veyard

1.76

Zone

1.71

maximum

1.67

atron

1.67

aurus

1.66

zone

1.65

 Explosion

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.