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

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

hello

-1.68

ozo

-1.64

 predicting

-1.62

bda

-1.58

raq

-1.58

-'

-1.54

��

-1.51

uga

-1.45

ovember

-1.42

MAD

-1.41

POSITIVE LOGITS

lux

1.74

 amenities

1.57

 branching

1.52

acent

1.50

adequ

1.50

ailable

1.50

 representatives

1.48

inate

1.47

autions

1.47

iguous

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.