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

0:0.04

1:0.05

2:0.13

3:0.10

4:0.12

5:0.05

6:0.08

7:0.10

8:0.06

9:0.06

10:0.08

11:0.07

Negative Logits

 novel

-1.81

 imagined

-1.80

 thought

-1.68

 gamb

-1.68

 ourselves

-1.67

 fiction

-1.66

fan

-1.61

 innov

-1.60

 adapt

-1.60

 unravel

-1.59

POSITIVE LOGITS

Alert

1.88

saf

1.87

retty

1.77

Sv

1.71

 Skydragon

1.71

龍喚士

1.71

 Attend

1.69

ategory

1.68

lvl

1.67

 Regist

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.