INDEX

Explanations

references to seasons and episodes of television shows

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.02

2:0.08

3:0.06

4:0.05

5:0.06

6:0.03

7:0.05

8:0.04

9:0.08

10:0.27

11:0.18

Negative Logits

soType

-1.18

 behavi

-1.12

igslist

-1.07

itarian

-1.07

rencies

-1.04

orgetown

-1.03

utsche

-1.03

��

-0.97

 extradition

-0.97

 straw

-0.95

POSITIVE LOGITS

 Preview

1.34

numbered

1.30

isode

1.23

odcast

1.19

 storyline

1.13

 previews

1.11

 FINAL

1.11

��

1.08

 Theme

1.07

 preview

1.05

Activations Density 0.137%

references to seasons and episodes of television shows

No Comments

No Known Activations