INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

4:0.09

5:0.08

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

ITS

-2.51

 Survival

-2.50

Wiki

-2.47

Sym

-2.23

Study

-2.23

COMPLE

-2.21

sym

-2.13

udic

-2.13

rity

-2.12

 researched

-2.06

POSITIVE LOGITS

 flirt

2.32

 holog

2.20

 presumptive

2.20

 hump

2.19

 greet

2.15

paw

2.13

 grin

2.10

 hairst

2.06

coy

2.05

 emoji

2.04

Activations Density 0.000%

No Known Activations

This feature has no known activations.