INDEX

Explanations

references to social class distinctions and generational comparisons

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.17

2:0.03

3:0.05

4:0.04

5:0.28

6:0.05

7:0.03

8:0.03

9:0.05

10:0.12

11:0.04

Negative Logits

 retracted

-2.10

Ao

-1.85

successfully

-1.77

 discl

-1.77

 CrossRef

-1.73

 executed

-1.70

 Edited

-1.69

 retrospect

-1.68

 Juno

-1.68

 copied

-1.68

POSITIVE LOGITS

ynes

2.28

landers

2.07

 Venezuel

2.02

 millionaires

1.98

女

1.89

iah

1.82

vill

1.81

 disenfranch

1.80

igrants

1.79

itizens

1.79

Activations Density 0.000%

references to social class distinctions and generational comparisons

No Comments

No Known Activations