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

1:0.07

2:0.07

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

IRE

-1.82

owsky

-1.80

untled

-1.75

redit

-1.74

ornia

-1.66

je

-1.65

Neg

-1.65

 cheated

-1.63

 faked

-1.60

 outright

-1.60

POSITIVE LOGITS

.}

1.85

imum

1.68

 subdu

1.66

 diagn

1.63

 arming

1.62

utic

1.62

aunders

1.58

 indo

1.54

 superv

1.52

ivities

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.