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

1:0.08

2:0.09

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.06

10:0.07

11:0.09

Negative Logits

Ley

-1.65

 Bloom

-1.62

 Carney

-1.56

 Museum

-1.54

 Peters

-1.53

chin

-1.47

 Lamp

-1.47

Strike

-1.42

nda

-1.41

 Probe

-1.40

POSITIVE LOGITS

ynchronous

1.85

ensical

1.74

 behaviors

1.69

 attrition

1.67

ipel

1.66

 sqor

1.57

ationally

1.55

 behaviours

1.55

 contingency

1.51

 causal

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.