INDEX

Explanations

references to organizations or institutions

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

0:0.24

1:0.04

2:0.01

3:0.08

4:0.08

5:0.07

6:0.07

7:0.02

8:0.23

9:0.04

10:0.02

11:0.05

Negative Logits

 Lego

-1.86

 opener

-1.72

 driver

-1.66

 multimedia

-1.65

 wheelchair

-1.64

 interpreter

-1.64

 multit

-1.63

 builder

-1.56

 narrator

-1.54

 prescription

-1.52

POSITIVE LOGITS

██

2.66

█

2.36

████

2.30

█

2.27

TAIN

2.10

в

2.06

OUN

2.05

REDACTED

1.98

RESULTS

1.95

1.88

Activations Density 0.000%

references to organizations or institutions

No Comments

No Known Activations