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

2:0.09

3:0.09

4:0.08

5:0.07

6:0.08

7:0.07

8:0.10

9:0.07

10:0.07

11:0.07

Negative Logits

twitch

-1.66

esian

-1.59

handed

-1.58

uner

-1.57

different

-1.57

oreal

-1.54

aneously

-1.52

opolis

-1.51

esis

-1.51

etically

-1.50

POSITIVE LOGITS

itars

1.79

obbies

1.66

itures

1.52

 Units

1.51

 GOODMAN

1.47

Champ

1.44

allery

1.43

WER

1.40

VI

1.38

UK

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.