INDEX

Explanations

temporal references indicating specific moments in time

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.10

7:0.10

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

�

-1.88

++)

-1.60

��

-1.59

shock

-1.56

jee

-1.55

ippy

-1.50

alde

-1.46

ldom

-1.46

weet

-1.45

 Doodle

-1.42

POSITIVE LOGITS

regation

1.67

 shipment

1.65

 Classification

1.63

 whistleblower

1.54

rification

1.52

 pipeline

1.50

ressor

1.47

 which

1.43

 staffing

1.42

 effectively

1.42

Activations Density 0.000%

temporal references indicating specific moments in time

No Comments

No Known Activations