INDEX

Explanations

negative evaluations or comparisons, particularly in the context of performance or quality

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

0:0.01

1:0.02

2:0.08

3:0.32

4:0.01

5:0.01

6:0.14

7:0.10

8:0.04

9:0.07

10:0.05

11:0.08

Negative Logits

unal

-1.34

aepernick

-1.26

agg

-1.13

ryu

-1.10

same

-1.08

mand

-1.06

nexus

-1.06

 truce

-1.02

Love

-1.02

elcome

-1.01

POSITIVE LOGITS

 charts

1.22

 iceberg

1.12

 ital

1.11

tein

1.11

 Rise

1.05

react

1.05

Rai

1.05

 Carbuncle

1.04

 earners

1.04

 Rend

1.04

Activations Density 0.039%

negative evaluations or comparisons, particularly in the context of performance or quality

No Comments

No Known Activations