INDEX

Explanations

negative contractions indicating denial or inability

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

0:0.07

1:0.12

2:0.03

3:0.03

4:0.03

5:0.27

6:0.03

7:0.02

8:0.14

9:0.06

10:0.05

11:0.08

Negative Logits

 prov

-1.57

ary

-1.56

 bearer

-1.55

 Guests

-1.47

 pros

-1.45

 coinc

-1.43

 guests

-1.42

 masc

-1.38

 furn

-1.38

 simultane

-1.37

POSITIVE LOGITS

iken

1.76

pload

1.69

umph

1.68

ynt

1.67

tty

1.66

tun

1.65

ndum

1.64

lance

1.64

hid

1.60

bench

1.60

Activations Density 0.021%

negative contractions indicating denial or inability

No Comments

No Known Activations