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

0:0.07

1:0.06

2:0.10

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.09

9:0.09

10:0.07

11:0.07

Negative Logits

 documenting

-1.81

 offending

-1.77

 photograp

-1.69

 reviewer

-1.66

 exposes

-1.61

 lull

-1.58

 contrasts

-1.58

 expose

-1.58

覚醒

-1.58

 prosecutions

-1.58

POSITIVE LOGITS

Already

1.94

rik

1.88

Eps

1.85

Beta

1.79

tu

1.67

omaly

1.65

xxxxxxxx

1.64

 Entered

1.64

RED

1.63

ept

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.