INDEX

Explanations

terms related to actions and processes in various contexts

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.03

2:0.09

3:0.08

4:0.02

5:0.05

6:0.06

7:0.17

8:0.06

9:0.21

10:0.07

11:0.08

Negative Logits

itched

-1.29

joice

-1.21

-1.17

 Option

-1.13

 Chev

-1.09

osponsors

-1.08

ordered

-1.06

 Choice

-1.05

ierre

-1.05

ivas

-1.02

POSITIVE LOGITS

ertodd

1.31

aceous

1.30

 Mueller

1.16

 Alonso

1.15

que

1.15

rior

1.12

 escalate

1.10

sonian

1.10

 McMaster

1.08

anda

1.07

Activations Density 0.027%

terms related to actions and processes in various contexts

No Comments

No Known Activations