INDEX

Explanations

phrases related to time and dates

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

0:0.07

1:0.06

2:0.09

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.07

Negative Logits

ullivan

-3.94

kefeller

-3.72

igham

-3.12

ormons

-3.11

oros

-3.07

Clinton

-3.02

angelo

-3.00

 Rove

-2.96

plom

-2.89

semble

-2.80

POSITIVE LOGITS

 curfew

3.08

 psychiat

2.89

 behavi

2.89

 Chronic

2.88

 behavioural

2.85

 Incident

2.79

nep

2.78

 Autism

2.75

Veh

2.71

DAC

2.67

Activations Density 0.000%

phrases related to time and dates

No Comments

No Known Activations