INDEX

Explanations

phrases that involve questioning or making inquiries about a subject

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.01

1:0.02

2:0.15

3:0.10

4:0.01

5:0.03

6:0.15

7:0.10

8:0.17

9:0.10

10:0.05

11:0.05

Negative Logits

��

-1.22

aughs

-1.17

wives

-1.11

leground

-1.11

 Corpus

-1.06

��

-1.04

 Torment

-1.02

rolled

-1.01

held

-1.01

QB

-1.00

POSITIVE LOGITS

ynthesis

1.12

 precedence

1.03

 follow

1.03

otin

1.03

andom

0.96

rule

0.95

 flourish

0.95

 abound

0.94

 ripple

0.94

 implication

0.93

Activations Density 0.026%

phrases that involve questioning or making inquiries about a subject

No Comments

No Known Activations