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

0:0.09

1:0.05

2:0.07

3:0.09

4:0.10

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

 served

-1.80

 Dragonbound

-1.69

 evacuated

-1.64

 dared

-1.63

 Spiegel

-1.63

ointed

-1.63

 ascended

-1.60

 Knight

-1.60

 preceded

-1.57

 accompanied

-1.57

POSITIVE LOGITS

oward

2.06

pots

1.96

inate

1.79

angles

1.79

flows

1.70

ollah

1.62

existing

1.61

SY

1.61

alin

1.59

angle

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.