INDEX

Explanations

comparative phrases and structures indicating relationships between concepts or items

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

1:0.02

2:0.11

3:0.07

4:0.17

5:0.03

6:0.03

7:0.31

8:0.05

9:0.02

10:0.04

11:0.08

Negative Logits

���

-1.70

mbuds

-1.68

ctors

-1.58

fox

-1.54

��

-1.52

osph

-1.50

ildo

-1.46

ogun

-1.45

alls

-1.43

 screened

-1.42

POSITIVE LOGITS

 Perspect

1.73

 origins

1.68

 precedence

1.62

 symbolism

1.58

 Shine

1.57

 genesis

1.54

 scarcity

1.51

 ingenuity

1.47

 obscurity

1.45

 profitability

1.42

Activations Density 0.002%

comparative phrases and structures indicating relationships between concepts or items

No Comments

No Known Activations