INDEX

Explanations

details related to conditions or requirements within specific regulatory or legal contexts

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.04

1:0.40

2:0.05

3:0.08

4:0.04

5:0.05

6:0.04

7:0.09

8:0.04

9:0.04

10:0.04

11:0.03

Negative Logits

anto

-2.92

ITIES

-2.61

pheus

-2.55

yth

-2.45

ocking

-2.40

erva

-2.40

yne

-2.34

�醒

-2.31

mbudsman

-2.31

antics

-2.30

POSITIVE LOGITS

 certain

6.97

 particular

6.50

 specific

6.44

certain

5.58

 Certain

5.14

Certain

5.08

 Specific

4.79

 specified

4.35

Specific

4.22

specific

4.14

Activations Density 0.063%

details related to conditions or requirements within specific regulatory or legal contexts

No Comments

No Known Activations