INDEX

Explanations

phrases indicating approval or positive sentiment

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.40

1:0.03

2:0.00

3:0.04

4:0.21

5:0.05

6:0.06

7:0.02

8:0.06

9:0.06

10:0.01

11:0.02

Negative Logits

esa

-2.06

IELD

-2.02

ipe

-1.75

dinand

-1.73

iple

-1.71

ipal

-1.64

mediate

-1.63

apeake

-1.61

abwe

-1.59

Bil

-1.56

POSITIVE LOGITS

�

2.22

;)

2.18

).

2.01

�

1.97

:)

1.94

!!!

1.86

huh

1.86

!!

1.86

!!!!

1.84

:-)

1.79

Activations Density 0.000%

phrases indicating approval or positive sentiment

No Comments

No Known Activations