INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

1:0.07

2:0.08

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.07

9:0.07

10:0.09

11:0.10

Negative Logits

iannopoulos

-1.99

thood

-1.97

aquin

-1.90

llo

-1.89

iatrics

-1.87

aiden

-1.85

arium

-1.81

udi

-1.78

inis

-1.76

iasis

-1.70

POSITIVE LOGITS

 semblance

1.64

sep

1.63

 recess

1.62

 horizontal

1.61

 phased

1.59

 backward

1.57

 mirror

1.55

 directional

1.54

 predictable

1.54

 brick

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.