INDEX

Explanations

the use of the verb "go" in the context of actions or movements

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

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

potion

-2.63

quarters

-2.47

olon

-2.34

psey

-2.32

anz

-2.19

enza

-2.18

aunder

-2.16

ann

-2.16

arez

-2.13

azo

-2.12

POSITIVE LOGITS

BIL

2.04

 Commando

2.03

 Tycoon

2.01

 calcul

1.99

 Wrong

1.97

KT

1.97

 Tuls

1.96

 Gear

1.96

さ

1.93

 grit

1.91

Activations Density 0.000%

the use of the verb "go" in the context of actions or movements

No Comments

No Known Activations