INDEX

Explanations

words expressing direction or purpose

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

0:0.08

1:0.08

2:0.07

3:0.09

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Dwight

-2.87

 Stafford

-2.68

isle

-2.65

 Hallow

-2.63

sonian

-2.58

 Hollow

-2.54

 Farn

-2.44

quickShipAvailable

-2.43

 Hicks

-2.42

Travel

-2.41

POSITIVE LOGITS

��

3.03

 GOODMAN

2.95

 combatants

2.77

 cannabinoids

2.77

 transsexual

2.76

 lawfully

2.71

��

2.68

MEP

2.60

 antibodies

2.51

®,

2.51

Activations Density 0.000%

words expressing direction or purpose

No Comments

No Known Activations