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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

rack

-1.62

tech

-1.60

iar

-1.59

wered

-1.58

eless

-1.57

 guessed

-1.54

ヘ

-1.52

Knight

-1.51

 Torch

-1.48

Intel

-1.44

POSITIVE LOGITS

 dependence

1.84

ependent

1.70

 fraught

1.64

\<

1.60

onse

1.59

ptoms

1.51

 Situation

1.50

 battleground

1.48

AMY

1.47

 dependency

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.