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

0:0.15

1:0.19

2:0.07

3:0.05

4:0.06

5:0.06

6:0.08

7:0.03

8:0.04

9:0.05

10:0.08

11:0.08

Negative Logits

�

-2.63

lest

-2.09

nai

-2.04

mart

-1.94

acus

-1.90

ouses

-1.89

paren

-1.88

���

-1.84

Es

-1.82

olin

-1.82

POSITIVE LOGITS

SPONSORED

1.92

 vote

1.91

 trend

1.87

 liking

1.87

seq

1.85

 Request

1.78

 funding

1.74

 bounty

1.73

lap

1.72

 karma

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.