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

2:0.10

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

orst

-1.82

iffe

-1.69

rero

-1.68

ificate

-1.66

 Romeo

-1.57

 Salem

-1.54

digy

-1.53

 Costa

-1.48

 flagged

-1.46

Untitled

-1.45

POSITIVE LOGITS

 mathemat

1.91

 horm

1.88

 cryst

1.87

ODY

1.83

 autonomy

1.77

ntil

1.76

 Rohing

1.73

ynchronous

1.72

 enthusi

1.69

clerosis

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.