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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.04

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.06

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 referen

-1.67

 secession

-1.64

 separat

-1.62

 treasurer

-1.61

 conspiracy

-1.59

 jihad

-1.56

 libertarian

-1.55

 trademark

-1.51

 intimidation

-1.51

 refusal

-1.51

POSITIVE LOGITS

bil

2.21

@@

2.07

ricia

2.01

rients

1.83

zac

1.77

 Downs

1.70

ubs

1.69

eval

1.69

eger

1.67

ials

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.