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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

teness

-1.72

 leukemia

-1.67

 srfAttach

-1.66

 Genocide

-1.60

 Brill

-1.57

��

-1.56

edom

-1.54

profits

-1.50

 Diseases

-1.49

 regress

-1.49

POSITIVE LOGITS

ocr

1.76

pin

1.76

pill

1.75

plug

1.73

pine

1.70

anqu

1.69

 vape

1.68

icone

1.68

hello

1.64

vic

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.