INDEX

Explanations

references to lists or categories

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

0:0.04

1:0.02

2:0.09

3:0.07

4:0.08

5:0.03

6:0.12

7:0.20

8:0.03

9:0.04

10:0.15

11:0.06

Negative Logits

ilet

-1.73

otine

-1.69

edin

-1.68

unte

-1.67

ombat

-1.60

ews

-1.56

chat

-1.55

 Quit

-1.54

isec

-1.52

osh

-1.51

POSITIVE LOGITS

 Glac

1.61

1.59

1.57

 Lands

1.54

1.53

eatures

1.50

1.47

lust

1.45

 Franz

1.45

Activations Density 0.000%

references to lists or categories

No Comments

No Known Activations