INDEX

Explanations

evaluative ratings and recommendations for products

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

0:0.06

1:0.02

2:0.04

3:0.08

4:0.09

5:0.05

6:0.30

7:0.07

8:0.03

9:0.08

10:0.04

11:0.09

Negative Logits

staking

-2.80

 Marketable

-2.45

 Court

-2.38

 fields

-2.36

 constituencies

-2.31

 mobilized

-2.30

 enacted

-2.30

 hatched

-2.29

porary

-2.28

govtrack

-2.28

POSITIVE LOGITS

review

5.15

 reviewer

5.08

 review

4.81

 reviewers

4.64

 reviews

4.62

 rave

4.16

Review

4.16

 Reviews

4.11

reviewed

3.97

 Rating

3.74

Activations Density 0.297%

evaluative ratings and recommendations for products

No Comments

No Known Activations