INDEX

Explanations

references to the television show "Saturday Night Live."

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

1:0.03

2:0.07

3:0.27

4:0.03

5:0.03

6:0.15

7:0.14

8:0.04

9:0.06

10:0.06

11:0.05

Negative Logits

lessly

-1.27

emonic

-1.22

rency

-1.18

ascript

-1.16

rea

-1.14

iked

-1.10

imov

-1.07

unky

-1.06

ngth

-1.06

ately

-1.06

POSITIVE LOGITS

 Lumpur

1.28

�

1.25

 Skydragon

1.07

 Lights

1.07

Availability

1.06

prem

1.06

-->

1.05

Khe

1.05

urst

1.04

artist

1.03

Activations Density 0.012%

references to the television show "Saturday Night Live."

No Comments

No Known Activations