INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.08

1:0.07

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

ense

-2.18

Enhanced

-2.05

enses

-1.97

tackle

-1.87

Reading

-1.84

sat

-1.84

parts

-1.79

pas

-1.72

how

-1.69

Eva

-1.69

POSITIVE LOGITS

 conduc

2.01

 GOODMAN

1.99

 constitu

1.89

 multic

1.85

 condem

1.84

 aval

1.79

kefeller

1.73

Wi

1.71

 PubMed

1.70

 Regist

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.