INDEX

Explanations

statements regarding claims made in the past, particularly in a political context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.06

2:0.07

3:0.08

4:0.07

5:0.10

6:0.08

7:0.08

8:0.10

9:0.07

10:0.07

11:0.08

Negative Logits

ヘ

-1.87

 Loch

-1.58

ˈ

-1.57

 Dism

-1.52

idated

-1.52

-1.49

itars

-1.49

olog

-1.48

oqu

-1.44

pload

-1.43

POSITIVE LOGITS

obar

1.78

luck

1.72

ume

1.67

VO

1.61

�醒

1.55

ONSORED

1.51

)))

1.50

},"

1.49

.</

1.48

asio

1.47

Activations Density 0.000%

statements regarding claims made in the past, particularly in a political context

No Comments

No Known Activations