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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.09

5:0.09

6:0.07

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

 Kardash

-1.97

 Kardashian

-1.94

 tabl

-1.92

 cele

-1.91

 headlines

-1.89

 rumors

-1.88

 celebrities

-1.84

 Oprah

-1.82

 medications

-1.81

 slogans

-1.80

POSITIVE LOGITS

annot

2.23

adra

1.98

REM

1.95

inet

1.89

ateur

1.87

adapt

1.87

vere

1.82

yth

1.74

very

1.73

ogh

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.