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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.06

10:0.08

11:0.08

Negative Logits

 cane

-1.73

 intimidation

-1.71

%%%%

-1.69

 insensitive

-1.67

 toast

-1.60

 slurs

-1.60

 harassment

-1.60

orable

-1.60

 imitation

-1.60

 illeg

-1.56

POSITIVE LOGITS

 Yard

1.80

 Instit

1.76

Pub

1.74

 Extend

1.73

NCT

1.71

 Architects

1.71

 Solutions

1.70

onte

1.69

 downstream

1.68

 Aven

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.