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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Dragonbound

-1.67

 lecture

-1.64

nikov

-1.56

displayText

-1.55

 comments

-1.55

 invitation

-1.54

 lectures

-1.54

 info

-1.50

istine

-1.48

 sermon

-1.47

POSITIVE LOGITS

ometimes

1.84

ccording

1.83

everal

1.69

 ende

1.65

 Seym

1.64

ンジ

1.57

swick

1.56

ADRA

1.54

Osw

1.54

arios

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.