INDEX

Explanations

references to specific contextual elements or topics in a discourse

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

0:0.08

1:0.08

2:0.08

3:0.06

4:0.08

5:0.07

6:0.07

7:0.10

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

CPS

-2.94

 toile

-2.92

romy

-2.90

 cooper

-2.63

 horizont

-2.56

 Gund

-2.55

 Mond

-2.54

 Bett

-2.50

 coworkers

-2.44

 Span

-2.43

POSITIVE LOGITS

agate

3.20

 cipher

2.70

ghazi

2.70

 Benghazi

2.69

 Caesar

2.65

Bitcoin

2.64

bitcoin

2.63

chrome

2.60

 WordPress

2.60

 bitcoin

2.54

Activations Density 0.000%

references to specific contextual elements or topics in a discourse

No Comments

No Known Activations