INDEX

Explanations

phrases indicating reporting or stating actions

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.04

1:0.04

2:0.06

3:0.06

4:0.23

5:0.13

6:0.05

7:0.07

8:0.05

9:0.11

10:0.05

11:0.06

Negative Logits

)—

-3.13

matically

-2.64

 inexpl

-2.27

 traject

-2.25

 unavoid

-2.23

 tragically

-2.23

—

-2.14

],"

-2.11

REC

-2.11

olars

-2.06

POSITIVE LOGITS

 replied

3.08

Asked

3.04

quote

2.98

'.

2.96

 quoted

2.93

 confir

2.92

Quote

2.88

 quoting

2.88

 Asked

2.75

 "...

2.68

Activations Density 0.154%

phrases indicating reporting or stating actions

No Comments

No Known Activations