INDEX

Explanations

phrases that express disappointment or dissatisfaction

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

0:0.02

1:0.01

2:0.12

3:0.25

4:0.10

5:0.02

6:0.12

7:0.10

8:0.04

9:0.04

10:0.06

11:0.07

Negative Logits

catentry

-1.56

cember

-1.49

/?

-1.49

ilaterally

-1.49

)].

-1.45

 mesh

-1.40

oided

-1.36

/-

-1.36

 lear

-1.33

 depending

-1.31

POSITIVE LOGITS

 裏�

1.88

schild

1.85

 fame

1.75

 Leban

1.65

 damned

1.54

 Born

1.49

 Blessed

1.49

hatt

1.47

eming

1.42

 Manor

1.39

Activations Density 0.000%

phrases that express disappointment or dissatisfaction

No Comments

No Known Activations