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

0:0.07

1:0.09

2:0.09

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

—"

-1.71

etheless

-1.63

,—

-1.57

 spouses

-1.57

 affair

-1.55

anooga

-1.50

��

-1.50

 Party

-1.49

��

-1.46

NEC

-1.44

POSITIVE LOGITS

pmwiki

2.47

ITCH

1.75

illo

1.72

gaard

1.68

ickle

1.62

fo

1.60

 sqor

1.59

uld

1.56

TPPStreamerBot

1.56

 Chains

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.