INDEX

Explanations

the verb "go."

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.06

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

DonaldTrump

-2.60

_.

-2.28

Motion

-2.16

 skelet

-2.07

heses

-2.05

Topics

-1.99

anguage

-1.98

 porous

-1.97

EVA

-1.93

JP

-1.90

POSITIVE LOGITS

inity

2.01

 Rite

1.95

vana

1.93

antage

1.85

agi

1.80

 altru

1.78

 Slayer

1.77

 stakes

1.76

 WARN

1.76

handedly

1.73

Activations Density 0.000%

the verb "go."

No Comments

No Known Activations