INDEX

Explanations

punctuation, specifically commas

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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.07

5:0.10

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

+/-

-1.83

 Vinyl

-1.79

bitcoin

-1.78

MPG

-1.78

dash

-1.77

ZIP

-1.74

sale

-1.72

oplan

-1.66

pex

-1.64

RAM

-1.63

POSITIVE LOGITS

));

1.91

eca

1.62

 Brock

1.60

 Nikki

1.59

 unreliable

1.59

 haunt

1.59

);

1.49

 Athen

1.48

 collide

1.47

 unde

1.44

Activations Density 0.000%

punctuation, specifically commas

No Comments

No Known Activations