INDEX

Explanations

occurrences of extreme negative terms or events

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

idable

-2.87

pillar

-2.80

phys

-2.76

 veget

-2.72

yip

-2.71

rocal

-2.65

achelor

-2.65

 veterin

-2.64

ruby

-2.60

htaking

-2.45

POSITIVE LOGITS

 Karma

3.34

 Fargo

3.08

 Goals

2.93

 Blackburn

2.87

Pai

2.81

KS

2.78

 Goal

2.78

 Arcade

2.78

 Meridian

2.76

 Brut

2.76

Activations Density 0.000%

occurrences of extreme negative terms or events

No Comments

No Known Activations