INDEX

Explanations

terms and statistics related to migration and violence against women

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

0:0.02

1:0.01

2:0.08

3:0.34

4:0.07

5:0.03

6:0.02

7:0.04

8:0.05

9:0.08

10:0.12

11:0.07

Negative Logits

luaj

-2.06

��

-1.94

afort

-1.88

��

-1.87

?????-

-1.79

版

-1.74

FK

-1.68

PDATE

-1.65

 enthusi

-1.64

again

-1.64

POSITIVE LOGITS

/(

1.76

 repetitive

1.68

 inherently

1.64

 specified

1.64

 bodily

1.63

 certain

1.62

 purportedly

1.59

 combustion

1.59

[[

1.59

Activations Density 0.487%

terms and statistics related to migration and violence against women

No Comments

No Known Activations