INDEX

Explanations

expressions related to neutrality or impartiality in discussions or arguments

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

0:0.01

1:0.02

2:0.06

3:0.05

4:0.13

5:0.02

6:0.04

7:0.43

8:0.02

9:0.03

10:0.08

11:0.05

Negative Logits

noon

-1.64

oret

-1.61

jong

-1.61

dates

-1.55

days

-1.54

aturdays

-1.52

pict

-1.52

eday

-1.51

signed

-1.50

 Birthday

-1.47

POSITIVE LOGITS

 unfavorable

1.91

 hostilities

1.80

 favour

1.80

 hostile

1.70

 Flavoring

1.65

channelAvailability

1.61

 favor

1.54

 conflict

1.53

 bitterness

1.52

 hostility

1.51

Activations Density 0.001%

expressions related to neutrality or impartiality in discussions or arguments

No Comments

No Known Activations