INDEX

Explanations

punctuation marks and specific passes of dialogue or interactions in written text

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

0:0.05

1:0.10

2:0.04

3:0.04

4:0.03

5:0.03

6:0.05

7:0.42

8:0.04

9:0.04

10:0.05

11:0.05

Negative Logits

 Hasan

-2.91

 paran

-2.88

PAN

-2.80

 Allan

-2.77

 Morton

-2.77

 Apex

-2.73

 Fruit

-2.72

Lan

-2.72

pton

-2.69

Ott

-2.67

POSITIVE LOGITS

[&

2.91

luaj

2.87

jj

2.78

ieri

2.77

RBI

2.55

dylib

2.50

ertodd

2.41

Tuc

2.39

★★

2.35

;;;;;;;;;;;;

2.32

Activations Density 0.023%

punctuation marks and specific passes of dialogue or interactions in written text

No Comments

No Known Activations