INDEX

Explanations

sentences that convey legal actions and consequences

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.16

2:0.14

3:0.05

4:0.03

5:0.03

6:0.06

7:0.05

8:0.04

9:0.06

10:0.19

11:0.07

Negative Logits

 Break

-3.23

 Scorp

-3.08

 Grind

-3.06

 Franch

-2.89

 Discount

-2.86

 Crack

-2.85

 Stamp

-2.78

 Chap

-2.76

Bre

-2.70

 Modest

-2.69

POSITIVE LOGITS

5.00

il

4.45

ot

4.26

es

4.20

ie

4.17

om

3.96

ir

3.86

3.81

os

3.74

Activations Density 0.349%

sentences that convey legal actions and consequences

No Comments

No Known Activations