INDEX

Explanations

negation or denial phrases

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

inav

-1.85

drawn

-1.66

 sidx

-1.64

�

-1.60

icol

-1.57

jiang

-1.56

 Franch

-1.56

enne

-1.53

 Regions

-1.51

favorite

-1.50

POSITIVE LOGITS

‎

1.70

 Burnett

1.45

 unequivocally

1.42

 churn

1.38

%"

1.37

 abortion

1.34

 independently

1.33

 creep

1.31

"—

1.31

.,"

1.30

Activations Density 0.000%

negation or denial phrases

No Comments

No Known Activations