INDEX

Explanations

phrases indicating uncertainty or lack of clarity

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

2:0.10

3:0.13

4:0.08

5:0.02

6:0.28

7:0.09

8:0.04

9:0.03

10:0.06

11:0.06

Negative Logits

 subsequent

-1.30

cellaneous

-1.22

 Skydragon

-1.19

 margins

-1.17

 accompany

-1.14

 endeavour

-1.14

 concludes

-1.14

版

-1.13

izons

-1.10

 ranging

-1.10

POSITIVE LOGITS

 anymore

2.10

yet

1.93

necess

1.70

nor

1.59

actly

1.52

 entirely

1.49

isible

1.49

eem

1.44

 terribly

1.40

 bothered

1.35

Activations Density 0.130%

phrases indicating uncertainty or lack of clarity

No Comments

No Known Activations