INDEX

Explanations

references to specific individuals or player names in a sports context

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.09

1:0.07

2:0.09

3:0.07

4:0.08

5:0.07

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

tymology

-3.11

BMC

-2.79

uary

-2.65

 voic

-2.57

dial

-2.53

bc

-2.49

 honorary

-2.46

 Niger

-2.44

 edit

-2.43

ariat

-2.43

POSITIVE LOGITS

 seams

2.81

 nightmares

2.79

 itch

2.76

 Myst

2.68

 Cind

2.65

 ants

2.65

 Hers

2.62

 peanuts

2.58

MAT

2.56

 Hogwarts

2.56

Activations Density 0.000%

references to specific individuals or player names in a sports context

No Comments

No Known Activations