INDEX

Explanations

symbols or characters indicating specific actions or events

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

0:0.14

1:0.07

2:0.09

3:0.09

4:0.04

5:0.03

6:0.07

7:0.12

8:0.04

9:0.07

10:0.13

11:0.05

Negative Logits

 Boris

-3.03

 Grimes

-2.83

 Mell

-2.81

 Meredith

-2.76

Reb

-2.68

 Blasio

-2.66

 Pitch

-2.63

 Frankenstein

-2.63

 Nicola

-2.61

 Wiggins

-2.60

POSITIVE LOGITS

SEA

6.50

SEA

5.61

 Southeast

4.08

 Seah

4.07

outheast

3.74

SA

3.55

apore

3.52

OW

3.41

 seiz

3.40

Sea

3.33

Activations Density 0.000%

symbols or characters indicating specific actions or events

No Comments

No Known Activations