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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

affe

-1.71

 infographic

-1.52

 contestants

-1.49

 symb

-1.46

boa

-1.44

ba

-1.43

 Debor

-1.42

urtle

-1.41

 automakers

-1.41

 Byrne

-1.40

POSITIVE LOGITS

opal

1.79

cerning

1.76

displayText

1.75

views

1.75

tones

1.67

sts

1.66

dayName

1.59

istani

1.59

 drafts

1.58

nings

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.