INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

Jiu

-1.77

 seiz

-1.75

ECA

-1.74

interstitial

-1.68

WithNo

-1.67

aternity

-1.66

Hon

-1.66

gart

-1.65

 winners

-1.58

ysis

-1.57

POSITIVE LOGITS

 timestamp

1.80

 palp

1.77

XML

1.66

mire

1.66

istant

1.63

elsen

1.63

"/>

1.62

mb

1.58

ppm

1.54

 scripting

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.