INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.08

1:0.06

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

hemat

-1.80

conom

-1.71

 bribery

-1.69

Generic

-1.69

 anomal

-1.67

omach

-1.67

ricular

-1.66

═

-1.65

 epist

-1.62

building

-1.60

POSITIVE LOGITS

�

1.61

 Carney

1.60

Times

1.59

�

1.59

Vu

1.58

 Kathleen

1.53

 Scrib

1.53

 Insider

1.52

 clip

1.51

 https

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.