INDEX

Explanations

expressions of enjoyment or appreciation toward various subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

0:0.02

1:0.02

2:0.04

3:0.09

4:0.13

5:0.04

6:0.06

7:0.13

8:0.03

9:0.05

10:0.12

11:0.21

Negative Logits

ゴン

-1.44

aeper

-1.27

entity

-1.26

phrine

-1.20

�

-1.20

own

-1.19

aditional

-1.16

umbling

-1.16

ewitness

-1.15

 hurled

-1.13

POSITIVE LOGITS

natureconservancy

1.21

 tools

1.07

 Barron

1.07

UD

1.06

 Chap

1.05

 dearly

1.05

PP

1.04

hard

1.02

IF

1.02

vt

0.98

Activations Density 0.040%

expressions of enjoyment or appreciation toward various subjects

No Comments

No Known Activations